| { | |
| "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": 1.36014723777771, | |
| "learning_rate": 0.00018571428571428572, | |
| "loss": 9.4034, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 2.117264986038208, | |
| "learning_rate": 0.00017142857142857143, | |
| "loss": 8.9051, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 2.277207851409912, | |
| "learning_rate": 0.00015714285714285716, | |
| "loss": 8.3058, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.0491803278688525, | |
| "grad_norm": 1.9988380670547485, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 7.8175, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.3114754098360657, | |
| "grad_norm": 1.7698421478271484, | |
| "learning_rate": 0.00012857142857142858, | |
| "loss": 7.2821, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.5737704918032787, | |
| "grad_norm": 2.32663893699646, | |
| "learning_rate": 0.00011428571428571428, | |
| "loss": 7.4096, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.8360655737704918, | |
| "grad_norm": 1.4435824155807495, | |
| "learning_rate": 0.0001, | |
| "loss": 7.1488, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.098360655737705, | |
| "grad_norm": 1.5567710399627686, | |
| "learning_rate": 8.571428571428571e-05, | |
| "loss": 6.7253, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.360655737704918, | |
| "grad_norm": 1.3461309671401978, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 6.9232, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.6229508196721314, | |
| "grad_norm": 1.2633932828903198, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 6.7861, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.8852459016393444, | |
| "grad_norm": 0.7925029993057251, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 6.8389, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 3.1475409836065573, | |
| "grad_norm": 1.3408855199813843, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 6.5778, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 3.4098360655737707, | |
| "grad_norm": 1.250908613204956, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 6.8636, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 3.6721311475409837, | |
| "grad_norm": 1.3394016027450562, | |
| "learning_rate": 0.0, | |
| "loss": 6.9516, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 3.6721311475409837, | |
| "step": 28, | |
| "total_flos": 134754941373624.0, | |
| "train_loss": 7.424190691539219, | |
| "train_runtime": 121.6682, | |
| "train_samples_per_second": 4.011, | |
| "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": 134754941373624.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |