| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 157, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03184713375796178, | |
| "grad_norm": 40.78604947627245, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5775, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06369426751592357, | |
| "grad_norm": 8.368950744101049, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1247, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09554140127388536, | |
| "grad_norm": 9.457819678472001, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7369, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12738853503184713, | |
| "grad_norm": 5.641687715871123, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5158, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1592356687898089, | |
| "grad_norm": 5.418478301114858, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4339, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1910828025477707, | |
| "grad_norm": 5.045194163255571, | |
| "learning_rate": 2e-05, | |
| "loss": 0.463, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2229299363057325, | |
| "grad_norm": 4.781645335845452, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3769, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25477707006369427, | |
| "grad_norm": 5.347347835798862, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3619, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28662420382165604, | |
| "grad_norm": 4.246397453328318, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3027, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3184713375796178, | |
| "grad_norm": 4.33165925517153, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2415, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3503184713375796, | |
| "grad_norm": 3.844921413622979, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2504, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3821656050955414, | |
| "grad_norm": 6.45954282043095, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2317, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4140127388535032, | |
| "grad_norm": 4.385098986777501, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2197, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.445859872611465, | |
| "grad_norm": 4.208753643886586, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2132, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.47770700636942676, | |
| "grad_norm": 2.771863737776465, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2171, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5095541401273885, | |
| "grad_norm": 2.34352087689591, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2368, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5414012738853503, | |
| "grad_norm": 2.837909679350126, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2246, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5732484076433121, | |
| "grad_norm": 4.432629271419918, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2425, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6050955414012739, | |
| "grad_norm": 2.0628378042750244, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2084, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6369426751592356, | |
| "grad_norm": 3.2999762267826993, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1822, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6687898089171974, | |
| "grad_norm": 1.7122002214796863, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1756, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7006369426751592, | |
| "grad_norm": 3.2760105813071396, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2213, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.732484076433121, | |
| "grad_norm": 3.283904309843202, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2022, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7643312101910829, | |
| "grad_norm": 2.600480873861268, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2137, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7961783439490446, | |
| "grad_norm": 2.81626515746397, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1902, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8280254777070064, | |
| "grad_norm": 3.7954679627760846, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1856, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8598726114649682, | |
| "grad_norm": 3.872799664454645, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1763, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.89171974522293, | |
| "grad_norm": 3.284248984016964, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1994, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9235668789808917, | |
| "grad_norm": 3.307812812852979, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1542, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.9554140127388535, | |
| "grad_norm": 3.4547396546144338, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1916, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9872611464968153, | |
| "grad_norm": 2.4075546087603814, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1619, | |
| "step": 155 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 314, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 157, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1351253753856.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |