| { |
| "best_metric": 2.4635186195373535, |
| "best_model_checkpoint": "./drive/MyDrive/peptide_esm/checkpoint-10488", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 10488, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1, |
| "grad_norm": 0.7004187107086182, |
| "learning_rate": 7.5e-07, |
| "loss": 2.5303, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.19, |
| "grad_norm": 0.7539237141609192, |
| "learning_rate": 1.5e-06, |
| "loss": 2.5119, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.29, |
| "grad_norm": 0.9745526313781738, |
| "learning_rate": 2.25e-06, |
| "loss": 2.4899, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 0.6661661863327026, |
| "learning_rate": 3e-06, |
| "loss": 2.4903, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.7792529463768005, |
| "learning_rate": 2.9380677126341868e-06, |
| "loss": 2.4831, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.57, |
| "grad_norm": 2.211763381958008, |
| "learning_rate": 2.8762592898431047e-06, |
| "loss": 2.4785, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.67, |
| "grad_norm": 0.7369110584259033, |
| "learning_rate": 2.814450867052023e-06, |
| "loss": 2.4763, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 0.8026860952377319, |
| "learning_rate": 2.75251857968621e-06, |
| "loss": 2.4702, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 0.5967105627059937, |
| "learning_rate": 2.6905862923203965e-06, |
| "loss": 2.4703, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 0.68107670545578, |
| "learning_rate": 2.6286540049545828e-06, |
| "loss": 2.4699, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.46760630607605, |
| "eval_runtime": 181.2222, |
| "eval_samples_per_second": 823.095, |
| "eval_steps_per_second": 6.434, |
| "step": 5244 |
| }, |
| { |
| "epoch": 1.05, |
| "grad_norm": 1.064468502998352, |
| "learning_rate": 2.56672171758877e-06, |
| "loss": 2.4671, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.14, |
| "grad_norm": 1.5440330505371094, |
| "learning_rate": 2.5047894302229566e-06, |
| "loss": 2.4663, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.24, |
| "grad_norm": 0.913020133972168, |
| "learning_rate": 2.442857142857143e-06, |
| "loss": 2.4654, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.33, |
| "grad_norm": 0.8316154479980469, |
| "learning_rate": 2.3810487200660612e-06, |
| "loss": 2.4694, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.43, |
| "grad_norm": 0.6185809969902039, |
| "learning_rate": 2.3191164327002475e-06, |
| "loss": 2.4668, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.53, |
| "grad_norm": 1.1215540170669556, |
| "learning_rate": 2.2571841453344346e-06, |
| "loss": 2.4668, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.62, |
| "grad_norm": 0.6679463982582092, |
| "learning_rate": 2.195251857968621e-06, |
| "loss": 2.4681, |
| "step": 8500 |
| }, |
| { |
| "epoch": 1.72, |
| "grad_norm": 1.1260002851486206, |
| "learning_rate": 2.1333195706028075e-06, |
| "loss": 2.4639, |
| "step": 9000 |
| }, |
| { |
| "epoch": 1.81, |
| "grad_norm": 0.6827268004417419, |
| "learning_rate": 2.0713872832369942e-06, |
| "loss": 2.4631, |
| "step": 9500 |
| }, |
| { |
| "epoch": 1.91, |
| "grad_norm": 0.7196531891822815, |
| "learning_rate": 2.0095788604459126e-06, |
| "loss": 2.4644, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 2.4635186195373535, |
| "eval_runtime": 180.8599, |
| "eval_samples_per_second": 824.744, |
| "eval_steps_per_second": 6.447, |
| "step": 10488 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 26220, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "total_flos": 4.1949317916310464e+17, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
