| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3824091778202677, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0076481835564053535, | |
| "eval_loss": 10.363897323608398, | |
| "eval_runtime": 0.3349, | |
| "eval_samples_per_second": 164.213, | |
| "eval_steps_per_second": 83.599, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03824091778202677, | |
| "grad_norm": 0.052073944360017776, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3636, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07648183556405354, | |
| "grad_norm": 0.06964851170778275, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3633, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07648183556405354, | |
| "eval_loss": 10.363548278808594, | |
| "eval_runtime": 0.3168, | |
| "eval_samples_per_second": 173.599, | |
| "eval_steps_per_second": 88.378, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1147227533460803, | |
| "grad_norm": 0.07909376919269562, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3621, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15296367112810708, | |
| "grad_norm": 0.055342454463243484, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3562, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15296367112810708, | |
| "eval_loss": 10.362905502319336, | |
| "eval_runtime": 0.3155, | |
| "eval_samples_per_second": 174.326, | |
| "eval_steps_per_second": 88.748, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.19120458891013384, | |
| "grad_norm": 0.07391843944787979, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3575, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2294455066921606, | |
| "grad_norm": 0.08445325493812561, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3585, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2294455066921606, | |
| "eval_loss": 10.362415313720703, | |
| "eval_runtime": 0.425, | |
| "eval_samples_per_second": 129.398, | |
| "eval_steps_per_second": 65.875, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2676864244741874, | |
| "grad_norm": 0.05303255841135979, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3645, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.30592734225621415, | |
| "grad_norm": 0.061790041625499725, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.358, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.30592734225621415, | |
| "eval_loss": 10.362190246582031, | |
| "eval_runtime": 0.3165, | |
| "eval_samples_per_second": 173.76, | |
| "eval_steps_per_second": 88.46, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3441682600382409, | |
| "grad_norm": 0.0804908350110054, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3554, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3824091778202677, | |
| "grad_norm": 0.06598898768424988, | |
| "learning_rate": 0.0, | |
| "loss": 10.3568, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3824091778202677, | |
| "eval_loss": 10.362147331237793, | |
| "eval_runtime": 0.318, | |
| "eval_samples_per_second": 172.974, | |
| "eval_steps_per_second": 88.06, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 646545408000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |