| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004349953781741069, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.349953781741069e-05, | |
| "grad_norm": 1.012073040008545, | |
| "learning_rate": 2e-05, | |
| "loss": 11.4632, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.349953781741069e-05, | |
| "eval_loss": 2.6230649948120117, | |
| "eval_runtime": 564.2906, | |
| "eval_samples_per_second": 17.154, | |
| "eval_steps_per_second": 8.577, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.699907563482138e-05, | |
| "grad_norm": 0.858562171459198, | |
| "learning_rate": 4e-05, | |
| "loss": 11.4761, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00013049861345223207, | |
| "grad_norm": 0.8046978712081909, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3636, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013049861345223207, | |
| "eval_loss": 2.620979070663452, | |
| "eval_runtime": 564.6631, | |
| "eval_samples_per_second": 17.143, | |
| "eval_steps_per_second": 8.571, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00017399815126964275, | |
| "grad_norm": 1.0520446300506592, | |
| "learning_rate": 8e-05, | |
| "loss": 10.6318, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00021749768908705346, | |
| "grad_norm": 1.413762092590332, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3725, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00026099722690446414, | |
| "grad_norm": 1.4776657819747925, | |
| "learning_rate": 0.00012, | |
| "loss": 9.566, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00026099722690446414, | |
| "eval_loss": 2.508013963699341, | |
| "eval_runtime": 564.7183, | |
| "eval_samples_per_second": 17.141, | |
| "eval_steps_per_second": 8.571, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0003044967647218748, | |
| "grad_norm": 2.5418920516967773, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3554, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003479963025392855, | |
| "grad_norm": 2.3485240936279297, | |
| "learning_rate": 0.00016, | |
| "loss": 9.5877, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00039149584035669624, | |
| "grad_norm": 4.464426040649414, | |
| "learning_rate": 0.00018, | |
| "loss": 9.7393, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00039149584035669624, | |
| "eval_loss": 2.207545042037964, | |
| "eval_runtime": 563.8534, | |
| "eval_samples_per_second": 17.168, | |
| "eval_steps_per_second": 8.584, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004349953781741069, | |
| "grad_norm": 4.874852657318115, | |
| "learning_rate": 0.0002, | |
| "loss": 8.4572, | |
| "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": 4862853953617920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |