| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03619909502262444, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012066365007541479, | |
| "eval_loss": 2.383432388305664, | |
| "eval_runtime": 30.0672, | |
| "eval_samples_per_second": 11.607, | |
| "eval_steps_per_second": 5.82, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036199095022624436, | |
| "grad_norm": 1.1864396333694458, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3579, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007239819004524887, | |
| "grad_norm": 1.5393321514129639, | |
| "learning_rate": 0.00012, | |
| "loss": 2.178, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009653092006033183, | |
| "eval_loss": 2.1127257347106934, | |
| "eval_runtime": 29.2266, | |
| "eval_samples_per_second": 11.941, | |
| "eval_steps_per_second": 5.988, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01085972850678733, | |
| "grad_norm": 2.129002094268799, | |
| "learning_rate": 0.00018, | |
| "loss": 2.044, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014479638009049774, | |
| "grad_norm": 0.914394736289978, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.9121, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01809954751131222, | |
| "grad_norm": 1.1399174928665161, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.9006, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019306184012066366, | |
| "eval_loss": 1.8634064197540283, | |
| "eval_runtime": 29.3594, | |
| "eval_samples_per_second": 11.887, | |
| "eval_steps_per_second": 5.961, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02171945701357466, | |
| "grad_norm": 1.0238810777664185, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.9244, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025339366515837104, | |
| "grad_norm": 0.8491950631141663, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.683, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02895927601809955, | |
| "grad_norm": 1.0529344081878662, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.697, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02895927601809955, | |
| "eval_loss": 1.805045485496521, | |
| "eval_runtime": 29.4142, | |
| "eval_samples_per_second": 11.865, | |
| "eval_steps_per_second": 5.95, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03257918552036199, | |
| "grad_norm": 1.040789246559143, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.6825, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03619909502262444, | |
| "grad_norm": 0.975259006023407, | |
| "learning_rate": 0.0, | |
| "loss": 1.7497, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |