| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006063055780113177, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002021018593371059, | |
| "eval_loss": 2.123032331466675, | |
| "eval_runtime": 236.6008, | |
| "eval_samples_per_second": 8.808, | |
| "eval_steps_per_second": 4.404, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006063055780113178, | |
| "grad_norm": 3.1338932514190674, | |
| "learning_rate": 6e-05, | |
| "loss": 8.7251, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012126111560226355, | |
| "grad_norm": 2.535696029663086, | |
| "learning_rate": 0.00012, | |
| "loss": 7.3551, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016168148746968471, | |
| "eval_loss": 1.7895063161849976, | |
| "eval_runtime": 236.6772, | |
| "eval_samples_per_second": 8.805, | |
| "eval_steps_per_second": 4.403, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001818916734033953, | |
| "grad_norm": 5.0467047691345215, | |
| "learning_rate": 0.00018, | |
| "loss": 7.4483, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002425222312045271, | |
| "grad_norm": 5.255463123321533, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 6.3648, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0030315278900565883, | |
| "grad_norm": 2.216106653213501, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 5.8742, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0032336297493936943, | |
| "eval_loss": 1.366114854812622, | |
| "eval_runtime": 236.62, | |
| "eval_samples_per_second": 8.807, | |
| "eval_steps_per_second": 4.404, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003637833468067906, | |
| "grad_norm": 2.676602840423584, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.694, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004244139046079224, | |
| "grad_norm": 1.9780032634735107, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 4.9153, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004850444624090542, | |
| "grad_norm": 1.9625349044799805, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 5.4398, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004850444624090542, | |
| "eval_loss": 1.2876747846603394, | |
| "eval_runtime": 236.7206, | |
| "eval_samples_per_second": 8.804, | |
| "eval_steps_per_second": 4.402, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005456750202101859, | |
| "grad_norm": 2.144939661026001, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 5.0995, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006063055780113177, | |
| "grad_norm": 1.977967381477356, | |
| "learning_rate": 0.0, | |
| "loss": 4.9248, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.90434898870272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |