| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.6721311475409837, | |
| "eval_steps": 500, | |
| "global_step": 28, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 1.4118119478225708, | |
| "learning_rate": 0.00018571428571428572, | |
| "loss": 9.3975, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 2.1741275787353516, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 8.8959, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 2.2493510246276855, | |
| "learning_rate": 0.00015714285714285716, | |
| "loss": 8.3131, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.0491803278688525, | |
| "grad_norm": 1.9181139469146729, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 7.8024, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 1.6867899894714355, | |
| "learning_rate": 0.00012857142857142858, | |
| "loss": 7.2601, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.5737704918032787, | |
| "grad_norm": 2.1906182765960693, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 7.4024, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.8360655737704918, | |
| "grad_norm": 1.4529337882995605, | |
| "learning_rate": 0.0001, | |
| "loss": 7.1401, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.098360655737705, | |
| "grad_norm": 1.6584192514419556, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 6.7346, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.360655737704918, | |
| "grad_norm": 1.3222064971923828, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 6.9177, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "grad_norm": 1.2361630201339722, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 6.7813, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.8852459016393444, | |
| "grad_norm": 0.7813708186149597, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 6.8394, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 3.1475409836065573, | |
| "grad_norm": 1.2966777086257935, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 6.5763, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.4098360655737707, | |
| "grad_norm": 1.266758918762207, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 6.8629, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.6721311475409837, | |
| "grad_norm": 1.3423734903335571, | |
| "learning_rate": 0.0, | |
| "loss": 6.949, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.6721311475409837, | |
| "step": 28, | |
| "total_flos": 134293008899424.0, | |
| "train_loss": 7.4194753510611395, | |
| "train_runtime": 121.7101, | |
| "train_samples_per_second": 4.01, | |
| "train_steps_per_second": 0.23 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 28, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 134293008899424.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |