| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.028169014084507, | |
| "eval_steps": 54, | |
| "global_step": 432, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 3.684292793273926, | |
| "learning_rate": 1.267605633802817e-05, | |
| "loss": 1.2505, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.2407653331756592, | |
| "eval_runtime": 45.8057, | |
| "eval_samples_per_second": 4.912, | |
| "eval_steps_per_second": 1.244, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 3.201833724975586, | |
| "learning_rate": 2.535211267605634e-05, | |
| "loss": 1.0237, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.9248250126838684, | |
| "eval_runtime": 45.8228, | |
| "eval_samples_per_second": 4.91, | |
| "eval_steps_per_second": 1.244, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 3.254812002182007, | |
| "learning_rate": 3.802816901408451e-05, | |
| "loss": 0.8635, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.8418264985084534, | |
| "eval_runtime": 45.8187, | |
| "eval_samples_per_second": 4.911, | |
| "eval_steps_per_second": 1.244, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 6.0061445236206055, | |
| "learning_rate": 4.992175273865415e-05, | |
| "loss": 0.8251, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.8128283619880676, | |
| "eval_runtime": 45.8246, | |
| "eval_samples_per_second": 4.91, | |
| "eval_steps_per_second": 1.244, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 2.051769733428955, | |
| "learning_rate": 4.85133020344288e-05, | |
| "loss": 0.7319, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.7979817986488342, | |
| "eval_runtime": 45.8206, | |
| "eval_samples_per_second": 4.91, | |
| "eval_steps_per_second": 1.244, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.8865206241607666, | |
| "learning_rate": 4.710485133020345e-05, | |
| "loss": 0.7378, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.7992598414421082, | |
| "eval_runtime": 45.8261, | |
| "eval_samples_per_second": 4.91, | |
| "eval_steps_per_second": 1.244, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 3.751115560531616, | |
| "learning_rate": 4.569640062597809e-05, | |
| "loss": 0.7821, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 0.7822461128234863, | |
| "eval_runtime": 45.8329, | |
| "eval_samples_per_second": 4.909, | |
| "eval_steps_per_second": 1.244, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 3.493082046508789, | |
| "learning_rate": 4.428794992175274e-05, | |
| "loss": 0.7132, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.7789326906204224, | |
| "eval_runtime": 45.8189, | |
| "eval_samples_per_second": 4.911, | |
| "eval_steps_per_second": 1.244, | |
| "step": 432 | |
| } | |
| ], | |
| "logging_steps": 54, | |
| "max_steps": 2130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 54, | |
| "total_flos": 2.6335665460445184e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |