| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.030120481927710843, | |
| "eval_steps": 2, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002008032128514056, | |
| "grad_norm": 0.5873426795005798, | |
| "learning_rate": 2e-05, | |
| "loss": 6.1151, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002008032128514056, | |
| "eval_loss": 1.5243289470672607, | |
| "eval_runtime": 11.9397, | |
| "eval_samples_per_second": 17.588, | |
| "eval_steps_per_second": 8.794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004016064257028112, | |
| "grad_norm": 1.1125620603561401, | |
| "learning_rate": 4e-05, | |
| "loss": 6.2336, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004016064257028112, | |
| "eval_loss": 1.5242085456848145, | |
| "eval_runtime": 11.899, | |
| "eval_samples_per_second": 17.649, | |
| "eval_steps_per_second": 8.824, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006024096385542169, | |
| "grad_norm": 0.5667304396629333, | |
| "learning_rate": 6e-05, | |
| "loss": 6.3612, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008032128514056224, | |
| "grad_norm": 0.6462880373001099, | |
| "learning_rate": 8e-05, | |
| "loss": 6.2151, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008032128514056224, | |
| "eval_loss": 1.5222526788711548, | |
| "eval_runtime": 11.8568, | |
| "eval_samples_per_second": 17.711, | |
| "eval_steps_per_second": 8.856, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010040160642570281, | |
| "grad_norm": 0.6439549326896667, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6033, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "grad_norm": 1.0273263454437256, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 6.2224, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "eval_loss": 1.514455795288086, | |
| "eval_runtime": 11.9707, | |
| "eval_samples_per_second": 17.543, | |
| "eval_steps_per_second": 8.771, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014056224899598393, | |
| "grad_norm": 0.7513625025749207, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 5.5897, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "grad_norm": 0.9003206491470337, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 5.6233, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "eval_loss": 1.4975639581680298, | |
| "eval_runtime": 11.8994, | |
| "eval_samples_per_second": 17.648, | |
| "eval_steps_per_second": 8.824, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018072289156626505, | |
| "grad_norm": 0.8670149445533752, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 5.0963, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020080321285140562, | |
| "grad_norm": 1.8713542222976685, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4797, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020080321285140562, | |
| "eval_loss": 1.4782865047454834, | |
| "eval_runtime": 11.9189, | |
| "eval_samples_per_second": 17.619, | |
| "eval_steps_per_second": 8.81, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02208835341365462, | |
| "grad_norm": 1.0168466567993164, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 5.7733, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.024096385542168676, | |
| "grad_norm": 1.0794020891189575, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 5.7392, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.024096385542168676, | |
| "eval_loss": 1.4653736352920532, | |
| "eval_runtime": 11.9932, | |
| "eval_samples_per_second": 17.51, | |
| "eval_steps_per_second": 8.755, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02610441767068273, | |
| "grad_norm": 1.0890697240829468, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 5.7144, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028112449799196786, | |
| "grad_norm": 1.0109323263168335, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 5.9203, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.028112449799196786, | |
| "eval_loss": 1.460502028465271, | |
| "eval_runtime": 11.9047, | |
| "eval_samples_per_second": 17.64, | |
| "eval_steps_per_second": 8.82, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030120481927710843, | |
| "grad_norm": 1.0608059167861938, | |
| "learning_rate": 0.0, | |
| "loss": 6.6043, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5130560112427008.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |