| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01412928293889085, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001412928293889085, | |
| "grad_norm": 0.9927595257759094, | |
| "learning_rate": 2e-05, | |
| "loss": 44.2813, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001412928293889085, | |
| "eval_loss": 11.076643943786621, | |
| "eval_runtime": 1.1279, | |
| "eval_samples_per_second": 264.206, | |
| "eval_steps_per_second": 132.103, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00282585658777817, | |
| "grad_norm": 0.9892200827598572, | |
| "learning_rate": 4e-05, | |
| "loss": 44.3553, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0042387848816672555, | |
| "grad_norm": 0.9895350933074951, | |
| "learning_rate": 6e-05, | |
| "loss": 44.2978, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0042387848816672555, | |
| "eval_loss": 11.07655143737793, | |
| "eval_runtime": 0.6384, | |
| "eval_samples_per_second": 466.764, | |
| "eval_steps_per_second": 233.382, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00565171317555634, | |
| "grad_norm": 1.0016391277313232, | |
| "learning_rate": 8e-05, | |
| "loss": 44.3014, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007064641469445425, | |
| "grad_norm": 0.913105309009552, | |
| "learning_rate": 0.0001, | |
| "loss": 44.3583, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008477569763334511, | |
| "grad_norm": 1.0485588312149048, | |
| "learning_rate": 0.00012, | |
| "loss": 44.2542, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008477569763334511, | |
| "eval_loss": 11.075966835021973, | |
| "eval_runtime": 0.655, | |
| "eval_samples_per_second": 454.935, | |
| "eval_steps_per_second": 227.467, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009890498057223597, | |
| "grad_norm": 1.1208932399749756, | |
| "learning_rate": 0.00014, | |
| "loss": 44.2396, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01130342635111268, | |
| "grad_norm": 1.0517933368682861, | |
| "learning_rate": 0.00016, | |
| "loss": 44.2893, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012716354645001766, | |
| "grad_norm": 1.1171672344207764, | |
| "learning_rate": 0.00018, | |
| "loss": 44.331, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012716354645001766, | |
| "eval_loss": 11.075115203857422, | |
| "eval_runtime": 0.6817, | |
| "eval_samples_per_second": 437.111, | |
| "eval_steps_per_second": 218.556, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01412928293889085, | |
| "grad_norm": 1.0434719324111938, | |
| "learning_rate": 0.0002, | |
| "loss": 44.3299, | |
| "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": 7471104000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |