| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18758620689655173, | |
| "eval_steps": 17, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005517241379310344, | |
| "eval_loss": 3.884207010269165, | |
| "eval_runtime": 4.4659, | |
| "eval_samples_per_second": 68.296, | |
| "eval_steps_per_second": 8.733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016551724137931035, | |
| "grad_norm": 0.6788153648376465, | |
| "learning_rate": 3e-05, | |
| "loss": 3.8284, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03310344827586207, | |
| "grad_norm": 0.6769624352455139, | |
| "learning_rate": 6e-05, | |
| "loss": 3.7716, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0496551724137931, | |
| "grad_norm": 0.8537060618400574, | |
| "learning_rate": 9e-05, | |
| "loss": 3.8822, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06620689655172414, | |
| "grad_norm": 0.9294676780700684, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 3.7923, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08275862068965517, | |
| "grad_norm": 0.9163342118263245, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 3.315, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09379310344827586, | |
| "eval_loss": 3.4180614948272705, | |
| "eval_runtime": 4.4396, | |
| "eval_samples_per_second": 68.701, | |
| "eval_steps_per_second": 8.785, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0993103448275862, | |
| "grad_norm": 1.1075429916381836, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 3.3909, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11586206896551725, | |
| "grad_norm": 1.0358085632324219, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 3.0781, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13241379310344828, | |
| "grad_norm": 0.6941744685173035, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 3.1513, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1489655172413793, | |
| "grad_norm": 0.7888012528419495, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 2.815, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16551724137931034, | |
| "grad_norm": 0.6974669694900513, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 2.7661, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1820689655172414, | |
| "grad_norm": 0.7885407209396362, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 2.8794, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.18758620689655173, | |
| "eval_loss": 2.820341110229492, | |
| "eval_runtime": 4.4584, | |
| "eval_samples_per_second": 68.411, | |
| "eval_steps_per_second": 8.748, | |
| "step": 34 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2161279594659840.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |