| { | |
| "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": 2.3285062313079834, | |
| "learning_rate": 1.267605633802817e-05, | |
| "loss": 1.1087, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.081784725189209, | |
| "eval_runtime": 47.5144, | |
| "eval_samples_per_second": 4.735, | |
| "eval_steps_per_second": 1.2, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 2.4186954498291016, | |
| "learning_rate": 2.535211267605634e-05, | |
| "loss": 0.9427, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.8712989687919617, | |
| "eval_runtime": 47.5444, | |
| "eval_samples_per_second": 4.732, | |
| "eval_steps_per_second": 1.199, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 2.902656316757202, | |
| "learning_rate": 3.802816901408451e-05, | |
| "loss": 0.8388, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 0.8230953216552734, | |
| "eval_runtime": 47.5387, | |
| "eval_samples_per_second": 4.733, | |
| "eval_steps_per_second": 1.199, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 3.9097344875335693, | |
| "learning_rate": 4.992175273865415e-05, | |
| "loss": 0.8432, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 0.8080307245254517, | |
| "eval_runtime": 47.5301, | |
| "eval_samples_per_second": 4.734, | |
| "eval_steps_per_second": 1.199, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 2.2199742794036865, | |
| "learning_rate": 4.85133020344288e-05, | |
| "loss": 0.7545, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 0.7959627509117126, | |
| "eval_runtime": 47.5367, | |
| "eval_samples_per_second": 4.733, | |
| "eval_steps_per_second": 1.199, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.9745190143585205, | |
| "learning_rate": 4.710485133020345e-05, | |
| "loss": 0.7489, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 0.7911092638969421, | |
| "eval_runtime": 47.5409, | |
| "eval_samples_per_second": 4.733, | |
| "eval_steps_per_second": 1.199, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 2.9790360927581787, | |
| "learning_rate": 4.569640062597809e-05, | |
| "loss": 0.7786, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 0.7847146391868591, | |
| "eval_runtime": 47.5327, | |
| "eval_samples_per_second": 4.734, | |
| "eval_steps_per_second": 1.199, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 3.888979434967041, | |
| "learning_rate": 4.428794992175274e-05, | |
| "loss": 0.7473, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 0.7797746062278748, | |
| "eval_runtime": 47.5404, | |
| "eval_samples_per_second": 4.733, | |
| "eval_steps_per_second": 1.199, | |
| "step": 432 | |
| } | |
| ], | |
| "logging_steps": 54, | |
| "max_steps": 2130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 54, | |
| "total_flos": 2.708392535477453e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |