| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 77, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012987012987012988, | |
| "grad_norm": 2.5498344898223877, | |
| "learning_rate": 2.5e-05, | |
| "loss": 4.7663, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06493506493506493, | |
| "grad_norm": 2.774350881576538, | |
| "learning_rate": 0.000125, | |
| "loss": 4.7043, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12987012987012986, | |
| "grad_norm": 3.9560413360595703, | |
| "learning_rate": 0.00019958568425315314, | |
| "loss": 4.0675, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19480519480519481, | |
| "grad_norm": 3.9846060276031494, | |
| "learning_rate": 0.00019496396989003193, | |
| "loss": 3.0353, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 2.2558484077453613, | |
| "learning_rate": 0.00018544194045464886, | |
| "loss": 2.3784, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3246753246753247, | |
| "grad_norm": 0.9705212712287903, | |
| "learning_rate": 0.00017151095013548994, | |
| "loss": 1.9776, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.38961038961038963, | |
| "grad_norm": 0.6810367107391357, | |
| "learning_rate": 0.00015388986359155758, | |
| "loss": 1.695, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.5922189950942993, | |
| "learning_rate": 0.00013348796121709862, | |
| "loss": 1.5304, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 0.5001540780067444, | |
| "learning_rate": 0.00011135801860504749, | |
| "loss": 1.4319, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5844155844155844, | |
| "grad_norm": 0.4108904302120209, | |
| "learning_rate": 8.86419813949525e-05, | |
| "loss": 1.3664, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6493506493506493, | |
| "grad_norm": 0.4516855776309967, | |
| "learning_rate": 6.651203878290139e-05, | |
| "loss": 1.3354, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.3778669238090515, | |
| "learning_rate": 4.611013640844245e-05, | |
| "loss": 1.309, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7792207792207793, | |
| "grad_norm": 0.3914947509765625, | |
| "learning_rate": 2.8489049864510054e-05, | |
| "loss": 1.2981, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8441558441558441, | |
| "grad_norm": 0.370316743850708, | |
| "learning_rate": 1.4558059545351143e-05, | |
| "loss": 1.2884, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.3161383867263794, | |
| "learning_rate": 5.036030109968082e-06, | |
| "loss": 1.2853, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.974025974025974, | |
| "grad_norm": 0.29596462845802307, | |
| "learning_rate": 4.143157468468717e-07, | |
| "loss": 1.2788, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8376365900039673, | |
| "eval_runtime": 2.2411, | |
| "eval_samples_per_second": 6.247, | |
| "eval_steps_per_second": 0.446, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 77, | |
| "total_flos": 1.5573103901178593e+18, | |
| "train_loss": 1.9809850438848717, | |
| "train_runtime": 1063.0601, | |
| "train_samples_per_second": 37.02, | |
| "train_steps_per_second": 0.072 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 77, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5573103901178593e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |