| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.21202854230377166, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0163098878695209, | |
| "grad_norm": 1.024299144744873, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0301, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0163098878695209, | |
| "eval_loss": 1.1028916835784912, | |
| "eval_runtime": 37.9426, | |
| "eval_samples_per_second": 10.885, | |
| "eval_steps_per_second": 2.741, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0326197757390418, | |
| "grad_norm": 1.0952816009521484, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0255, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04892966360856269, | |
| "grad_norm": 0.874853789806366, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.005, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0652395514780836, | |
| "grad_norm": 0.7411254048347473, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9346, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08154943934760449, | |
| "grad_norm": 0.737731397151947, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.8497, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09785932721712538, | |
| "grad_norm": 0.7540619969367981, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8999, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11416921508664628, | |
| "grad_norm": 0.6454194784164429, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7982, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1304791029561672, | |
| "grad_norm": 0.5729678273200989, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.821, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14678899082568808, | |
| "grad_norm": 0.5690068602561951, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7976, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16309887869520898, | |
| "grad_norm": 0.524340033531189, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.84, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17940876656472987, | |
| "grad_norm": 0.47216275334358215, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.8479, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.19571865443425077, | |
| "grad_norm": 0.4617241621017456, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.791, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21202854230377166, | |
| "grad_norm": 0.5128786563873291, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8122, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.21202854230377166, | |
| "eval_loss": 0.8193792104721069, | |
| "eval_runtime": 38.0332, | |
| "eval_samples_per_second": 10.859, | |
| "eval_steps_per_second": 2.734, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.9250203895516365e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |