| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004808976756612343, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005343307507347048, | |
| "grad_norm": 2.1132009029388428, | |
| "learning_rate": 2e-05, | |
| "loss": 4.8582, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005343307507347048, | |
| "eval_loss": 1.1991479396820068, | |
| "eval_runtime": 44.4738, | |
| "eval_samples_per_second": 17.718, | |
| "eval_steps_per_second": 8.859, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010686615014694097, | |
| "grad_norm": 2.6152126789093018, | |
| "learning_rate": 4e-05, | |
| "loss": 3.9917, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016029922522041143, | |
| "grad_norm": 2.2400717735290527, | |
| "learning_rate": 6e-05, | |
| "loss": 4.6781, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016029922522041143, | |
| "eval_loss": 1.196653127670288, | |
| "eval_runtime": 44.4157, | |
| "eval_samples_per_second": 17.741, | |
| "eval_steps_per_second": 8.871, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021373230029388193, | |
| "grad_norm": 2.0583109855651855, | |
| "learning_rate": 8e-05, | |
| "loss": 4.3992, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0026716537536735237, | |
| "grad_norm": 3.2414333820343018, | |
| "learning_rate": 0.0001, | |
| "loss": 5.074, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032059845044082286, | |
| "grad_norm": 2.703151226043701, | |
| "learning_rate": 0.00012, | |
| "loss": 4.2035, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032059845044082286, | |
| "eval_loss": 1.16398286819458, | |
| "eval_runtime": 49.8632, | |
| "eval_samples_per_second": 15.803, | |
| "eval_steps_per_second": 7.902, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037403152551429334, | |
| "grad_norm": 3.2883031368255615, | |
| "learning_rate": 0.00014, | |
| "loss": 4.7999, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004274646005877639, | |
| "grad_norm": 3.0747218132019043, | |
| "learning_rate": 0.00016, | |
| "loss": 4.5372, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004808976756612343, | |
| "grad_norm": 3.0872762203216553, | |
| "learning_rate": 0.00018, | |
| "loss": 4.1399, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004808976756612343, | |
| "eval_loss": 1.0296658277511597, | |
| "eval_runtime": 47.1969, | |
| "eval_samples_per_second": 16.696, | |
| "eval_steps_per_second": 8.348, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2931719644643328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |