| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 52, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1371, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1372, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9980267284282718e-05, | |
| "loss": 0.0334, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9921147013144782e-05, | |
| "loss": 0.0446, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.982287250728689e-05, | |
| "loss": 0.0243, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9685831611286312e-05, | |
| "loss": 0.0224, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9510565162951538e-05, | |
| "loss": 0.0196, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9297764858882516e-05, | |
| "loss": 0.0205, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9048270524660197e-05, | |
| "loss": 0.0178, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.8763066800438638e-05, | |
| "loss": 0.0181, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.8443279255020153e-05, | |
| "loss": 0.0161, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.0174, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.7705132427757895e-05, | |
| "loss": 0.0147, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.7289686274214116e-05, | |
| "loss": 0.0165, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.684547105928689e-05, | |
| "loss": 0.0164, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.63742398974869e-05, | |
| "loss": 0.014, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.5877852522924733e-05, | |
| "loss": 0.0161, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.5358267949789968e-05, | |
| "loss": 0.0135, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.4817536741017153e-05, | |
| "loss": 0.0147, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.4257792915650728e-05, | |
| "loss": 0.0127, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.3681245526846782e-05, | |
| "loss": 0.0154, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.0141, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.2486898871648552e-05, | |
| "loss": 0.0145, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.187381314585725e-05, | |
| "loss": 0.0127, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.1253332335643043e-05, | |
| "loss": 0.0152, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.0627905195293135e-05, | |
| "loss": 0.0132, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0141, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.372094804706867e-06, | |
| "loss": 0.0134, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.746667664356957e-06, | |
| "loss": 0.0124, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.126186854142752e-06, | |
| "loss": 0.014, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.513101128351454e-06, | |
| "loss": 0.0127, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.0136, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.318754473153221e-06, | |
| "loss": 0.0115, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.742207084349274e-06, | |
| "loss": 0.0155, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.1824632589828465e-06, | |
| "loss": 0.0122, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.641732050210032e-06, | |
| "loss": 0.0142, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.12214747707527e-06, | |
| "loss": 0.0116, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.625760102513103e-06, | |
| "loss": 0.0131, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.1545289407131128e-06, | |
| "loss": 0.012, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.7103137257858867e-06, | |
| "loss": 0.0129, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.2948675722421086e-06, | |
| "loss": 0.0148, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.0114, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.5567207449798517e-06, | |
| "loss": 0.0131, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.2369331995613664e-06, | |
| "loss": 0.0127, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.517294753398066e-07, | |
| "loss": 0.0136, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.022351411174866e-07, | |
| "loss": 0.0121, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.894348370484648e-07, | |
| "loss": 0.0129, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.1416838871368925e-07, | |
| "loss": 0.0117, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.7712749271311392e-07, | |
| "loss": 0.013, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.885298685522235e-08, | |
| "loss": 0.0115, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.973271571728441e-08, | |
| "loss": 0.0137, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0119, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 52, | |
| "total_flos": 0.0, | |
| "train_loss": 0.020144037382963758, | |
| "train_runtime": 1639.7469, | |
| "train_samples_per_second": 64.947, | |
| "train_steps_per_second": 0.032 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 52, | |
| "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": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |