| { | |
| "best_metric": 1.621703028678894, | |
| "best_model_checkpoint": "output/the-the-pigs/checkpoint-132", | |
| "epoch": 11.0, | |
| "global_step": 132, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.292589525111794e-05, | |
| "loss": 2.5049, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.725216267546246e-05, | |
| "loss": 2.2501, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.966219425201416, | |
| "eval_runtime": 0.848, | |
| "eval_samples_per_second": 22.405, | |
| "eval_steps_per_second": 3.538, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.857716640189785e-06, | |
| "loss": 2.2537, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.686881626551516e-05, | |
| "loss": 2.1305, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00013520660867542716, | |
| "loss": 2.0792, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.9108868837356567, | |
| "eval_runtime": 0.8428, | |
| "eval_samples_per_second": 22.544, | |
| "eval_steps_per_second": 3.56, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00010756924162575734, | |
| "loss": 2.1293, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.9630758374242683e-05, | |
| "loss": 2.0062, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.830873966217041, | |
| "eval_runtime": 0.8441, | |
| "eval_samples_per_second": 22.51, | |
| "eval_steps_per_second": 3.554, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 1.9933913245728396e-06, | |
| "loss": 1.9324, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 6.033118373448485e-05, | |
| "loss": 1.9227, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 0.00012934228335981018, | |
| "loss": 1.9492, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.8247166872024536, | |
| "eval_runtime": 0.8513, | |
| "eval_samples_per_second": 22.319, | |
| "eval_steps_per_second": 3.524, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.00011994783732453755, | |
| "loss": 1.8601, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 4.42741047488822e-05, | |
| "loss": 1.7486, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.8994, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.7911409139633179, | |
| "eval_runtime": 0.8376, | |
| "eval_samples_per_second": 22.685, | |
| "eval_steps_per_second": 3.582, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 5.38, | |
| "learning_rate": 4.4274104748882125e-05, | |
| "loss": 1.7558, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 0.00011994783732453749, | |
| "loss": 1.8425, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.780040979385376, | |
| "eval_runtime": 0.8465, | |
| "eval_samples_per_second": 22.444, | |
| "eval_steps_per_second": 3.544, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 0.00012934228335981018, | |
| "loss": 1.72, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 6.54, | |
| "learning_rate": 6.033118373448493e-05, | |
| "loss": 1.7991, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 1.9933913245728244e-06, | |
| "loss": 1.7086, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.7639576196670532, | |
| "eval_runtime": 0.8412, | |
| "eval_samples_per_second": 22.587, | |
| "eval_steps_per_second": 3.566, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 2.963075837424261e-05, | |
| "loss": 1.6218, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 0.00010756924162575728, | |
| "loss": 1.6723, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.7437282800674438, | |
| "eval_runtime": 0.8437, | |
| "eval_samples_per_second": 22.521, | |
| "eval_steps_per_second": 3.556, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 8.08, | |
| "learning_rate": 0.0001352066086754272, | |
| "loss": 1.7365, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 7.68688162655152e-05, | |
| "loss": 1.6506, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 7.85771664018977e-06, | |
| "loss": 1.5713, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.7347867488861084, | |
| "eval_runtime": 0.851, | |
| "eval_samples_per_second": 22.327, | |
| "eval_steps_per_second": 3.525, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 0.0001372, | |
| "loss": 1.6342, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.6437487602233887, | |
| "eval_runtime": 0.9748, | |
| "eval_samples_per_second": 22.569, | |
| "eval_steps_per_second": 3.078, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 10.42, | |
| "learning_rate": 8.635498649403298e-05, | |
| "loss": 1.7365, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 10.83, | |
| "learning_rate": 9.190657300387535e-06, | |
| "loss": 1.6443, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.621703028678894, | |
| "eval_runtime": 1.0058, | |
| "eval_samples_per_second": 21.873, | |
| "eval_steps_per_second": 2.983, | |
| "step": 132 | |
| } | |
| ], | |
| "max_steps": 1308, | |
| "num_train_epochs": 109, | |
| "total_flos": 130384723968000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |