| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00014832558950151478, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.4832558950151478e-05, | |
| "grad_norm": 1106.373779296875, | |
| "learning_rate": 2e-05, | |
| "loss": 95.6979, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.4832558950151478e-05, | |
| "eval_loss": 23.534069061279297, | |
| "eval_runtime": 1949.8674, | |
| "eval_samples_per_second": 14.558, | |
| "eval_steps_per_second": 7.279, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.9665117900302956e-05, | |
| "grad_norm": 1290.805908203125, | |
| "learning_rate": 4e-05, | |
| "loss": 96.301, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.449767685045443e-05, | |
| "grad_norm": 1336.470458984375, | |
| "learning_rate": 6e-05, | |
| "loss": 94.7096, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.449767685045443e-05, | |
| "eval_loss": 23.524295806884766, | |
| "eval_runtime": 1952.0732, | |
| "eval_samples_per_second": 14.542, | |
| "eval_steps_per_second": 7.271, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.933023580060591e-05, | |
| "grad_norm": 1352.6219482421875, | |
| "learning_rate": 8e-05, | |
| "loss": 93.8438, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 7.416279475075739e-05, | |
| "grad_norm": 1339.363037109375, | |
| "learning_rate": 0.0001, | |
| "loss": 95.0979, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.899535370090886e-05, | |
| "grad_norm": 1209.0018310546875, | |
| "learning_rate": 0.00012, | |
| "loss": 94.5627, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 8.899535370090886e-05, | |
| "eval_loss": 23.490365982055664, | |
| "eval_runtime": 1965.3434, | |
| "eval_samples_per_second": 14.444, | |
| "eval_steps_per_second": 7.222, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00010382791265106034, | |
| "grad_norm": 1945.038330078125, | |
| "learning_rate": 0.00014, | |
| "loss": 92.7226, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00011866047160121182, | |
| "grad_norm": 976.50830078125, | |
| "learning_rate": 0.00016, | |
| "loss": 92.8456, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001334930305513633, | |
| "grad_norm": 1855.9024658203125, | |
| "learning_rate": 0.00018, | |
| "loss": 94.9168, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001334930305513633, | |
| "eval_loss": 23.42270278930664, | |
| "eval_runtime": 1955.5745, | |
| "eval_samples_per_second": 14.516, | |
| "eval_steps_per_second": 7.258, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00014832558950151478, | |
| "grad_norm": 1729.698974609375, | |
| "learning_rate": 0.0002, | |
| "loss": 94.6717, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 89372900720640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |