| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00047112587305513353, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.711258730551335e-05, | |
| "grad_norm": 0.8562235832214355, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0742, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.711258730551335e-05, | |
| "eval_loss": 2.2553226947784424, | |
| "eval_runtime": 311.258, | |
| "eval_samples_per_second": 28.716, | |
| "eval_steps_per_second": 14.358, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.42251746110267e-05, | |
| "grad_norm": 0.9954326152801514, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2179, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00014133776191654006, | |
| "grad_norm": 1.054620623588562, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1878, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014133776191654006, | |
| "eval_loss": 2.2517285346984863, | |
| "eval_runtime": 310.2646, | |
| "eval_samples_per_second": 28.808, | |
| "eval_steps_per_second": 14.404, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001884503492220534, | |
| "grad_norm": 1.0297633409500122, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5147, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00023556293652756677, | |
| "grad_norm": 1.0218156576156616, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8729, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00028267552383308013, | |
| "grad_norm": 1.0576367378234863, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1551, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00028267552383308013, | |
| "eval_loss": 2.1760523319244385, | |
| "eval_runtime": 310.4139, | |
| "eval_samples_per_second": 28.794, | |
| "eval_steps_per_second": 14.397, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00032978811113859347, | |
| "grad_norm": 1.233701229095459, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0872, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003769006984441068, | |
| "grad_norm": 1.4318066835403442, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1394, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00042401328574962014, | |
| "grad_norm": 1.458452820777893, | |
| "learning_rate": 0.00018, | |
| "loss": 1.783, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00042401328574962014, | |
| "eval_loss": 1.9945000410079956, | |
| "eval_runtime": 310.4496, | |
| "eval_samples_per_second": 28.791, | |
| "eval_steps_per_second": 14.395, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00047112587305513353, | |
| "grad_norm": 1.8195215463638306, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7586, | |
| "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": 1942042460553216.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |