| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.400200100050025, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02001000500250125, | |
| "grad_norm": 1.2456663846969604, | |
| "learning_rate": 4.999447296060165e-05, | |
| "loss": 1.3318, | |
| "num_input_tokens_seen": 15648, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0400200100050025, | |
| "grad_norm": 0.8590693473815918, | |
| "learning_rate": 4.997789428625975e-05, | |
| "loss": 1.2773, | |
| "num_input_tokens_seen": 28720, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.060030015007503754, | |
| "grad_norm": 0.8516742587089539, | |
| "learning_rate": 4.995027130745321e-05, | |
| "loss": 1.1401, | |
| "num_input_tokens_seen": 43808, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.080040020010005, | |
| "grad_norm": 1.0357950925827026, | |
| "learning_rate": 4.99116162380454e-05, | |
| "loss": 1.089, | |
| "num_input_tokens_seen": 57472, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10005002501250625, | |
| "grad_norm": 0.744416356086731, | |
| "learning_rate": 4.986194616988364e-05, | |
| "loss": 1.1176, | |
| "num_input_tokens_seen": 71968, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12006003001500751, | |
| "grad_norm": 0.7087241411209106, | |
| "learning_rate": 4.980128306524183e-05, | |
| "loss": 0.9949, | |
| "num_input_tokens_seen": 85552, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14007003501750875, | |
| "grad_norm": 0.708070695400238, | |
| "learning_rate": 4.972965374710952e-05, | |
| "loss": 1.0264, | |
| "num_input_tokens_seen": 100512, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16008004002001, | |
| "grad_norm": 0.7232606410980225, | |
| "learning_rate": 4.964708988733178e-05, | |
| "loss": 1.0004, | |
| "num_input_tokens_seen": 113376, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18009004502251125, | |
| "grad_norm": 1.207189679145813, | |
| "learning_rate": 4.9553627992605066e-05, | |
| "loss": 1.1137, | |
| "num_input_tokens_seen": 127680, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2001000500250125, | |
| "grad_norm": 0.6889365315437317, | |
| "learning_rate": 4.944930938833535e-05, | |
| "loss": 0.9646, | |
| "num_input_tokens_seen": 143136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22011005502751377, | |
| "grad_norm": 1.3263787031173706, | |
| "learning_rate": 4.9334180200365486e-05, | |
| "loss": 0.9757, | |
| "num_input_tokens_seen": 155488, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24012006003001501, | |
| "grad_norm": 1.0919948816299438, | |
| "learning_rate": 4.9208291334580104e-05, | |
| "loss": 0.9126, | |
| "num_input_tokens_seen": 171008, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.26013006503251623, | |
| "grad_norm": 0.853539764881134, | |
| "learning_rate": 4.907169845439688e-05, | |
| "loss": 1.0119, | |
| "num_input_tokens_seen": 185536, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2801400700350175, | |
| "grad_norm": 0.9023884534835815, | |
| "learning_rate": 4.892446195615423e-05, | |
| "loss": 1.1192, | |
| "num_input_tokens_seen": 201728, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3001500750375188, | |
| "grad_norm": 1.3300387859344482, | |
| "learning_rate": 4.87666469424063e-05, | |
| "loss": 1.0167, | |
| "num_input_tokens_seen": 217584, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.32016008004002, | |
| "grad_norm": 1.1315807104110718, | |
| "learning_rate": 4.859832319313697e-05, | |
| "loss": 0.8291, | |
| "num_input_tokens_seen": 230864, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3401700850425213, | |
| "grad_norm": 1.2459896802902222, | |
| "learning_rate": 4.841956513490577e-05, | |
| "loss": 0.9591, | |
| "num_input_tokens_seen": 245584, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3601800900450225, | |
| "grad_norm": 1.114758849143982, | |
| "learning_rate": 4.8230451807939135e-05, | |
| "loss": 0.9869, | |
| "num_input_tokens_seen": 259760, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.38019009504752377, | |
| "grad_norm": 0.8792176842689514, | |
| "learning_rate": 4.803106683118177e-05, | |
| "loss": 1.0423, | |
| "num_input_tokens_seen": 274432, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.400200100050025, | |
| "grad_norm": 1.6365342140197754, | |
| "learning_rate": 4.782149836532345e-05, | |
| "loss": 1.0122, | |
| "num_input_tokens_seen": 288256, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 747, | |
| "num_input_tokens_seen": 288256, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3016308396326912e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |