| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.788732394366197, | |
| "eval_steps": 54, | |
| "global_step": 594, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 2.052495241165161, | |
| "learning_rate": 1.267605633802817e-05, | |
| "loss": 1.5181, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.4102150201797485, | |
| "eval_runtime": 58.6295, | |
| "eval_samples_per_second": 3.838, | |
| "eval_steps_per_second": 0.972, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 2.247065782546997, | |
| "learning_rate": 2.535211267605634e-05, | |
| "loss": 1.3096, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.2001529932022095, | |
| "eval_runtime": 58.6195, | |
| "eval_samples_per_second": 3.838, | |
| "eval_steps_per_second": 0.972, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.313900947570801, | |
| "learning_rate": 3.802816901408451e-05, | |
| "loss": 1.191, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.1402766704559326, | |
| "eval_runtime": 58.6237, | |
| "eval_samples_per_second": 3.838, | |
| "eval_steps_per_second": 0.972, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 2.6796553134918213, | |
| "learning_rate": 4.992175273865415e-05, | |
| "loss": 1.1728, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.1215072870254517, | |
| "eval_runtime": 58.628, | |
| "eval_samples_per_second": 3.838, | |
| "eval_steps_per_second": 0.972, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 2.153010845184326, | |
| "learning_rate": 4.85133020344288e-05, | |
| "loss": 1.088, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.106386423110962, | |
| "eval_runtime": 58.608, | |
| "eval_samples_per_second": 3.839, | |
| "eval_steps_per_second": 0.973, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.141529083251953, | |
| "learning_rate": 4.710485133020345e-05, | |
| "loss": 1.1081, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.095576286315918, | |
| "eval_runtime": 58.6271, | |
| "eval_samples_per_second": 3.838, | |
| "eval_steps_per_second": 0.972, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 2.5019514560699463, | |
| "learning_rate": 4.569640062597809e-05, | |
| "loss": 1.138, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 1.089218020439148, | |
| "eval_runtime": 58.6083, | |
| "eval_samples_per_second": 3.839, | |
| "eval_steps_per_second": 0.973, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 2.8438944816589355, | |
| "learning_rate": 4.428794992175274e-05, | |
| "loss": 1.0855, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 1.0866470336914062, | |
| "eval_runtime": 58.5985, | |
| "eval_samples_per_second": 3.84, | |
| "eval_steps_per_second": 0.973, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 2.4683525562286377, | |
| "learning_rate": 4.287949921752739e-05, | |
| "loss": 1.0292, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 1.0852150917053223, | |
| "eval_runtime": 58.6647, | |
| "eval_samples_per_second": 3.835, | |
| "eval_steps_per_second": 0.972, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "grad_norm": 3.097724676132202, | |
| "learning_rate": 4.1471048513302035e-05, | |
| "loss": 1.0259, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "eval_loss": 1.0849454402923584, | |
| "eval_runtime": 58.6693, | |
| "eval_samples_per_second": 3.835, | |
| "eval_steps_per_second": 0.972, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 2.5000972747802734, | |
| "learning_rate": 4.0062597809076686e-05, | |
| "loss": 1.0284, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_loss": 1.0797874927520752, | |
| "eval_runtime": 58.6773, | |
| "eval_samples_per_second": 3.835, | |
| "eval_steps_per_second": 0.971, | |
| "step": 594 | |
| } | |
| ], | |
| "logging_steps": 54, | |
| "max_steps": 2130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 54, | |
| "total_flos": 4.744730322350899e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |