| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9878542510121457, | |
| "eval_steps": 500, | |
| "global_step": 246, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08097165991902834, | |
| "grad_norm": 1034.3036354530775, | |
| "learning_rate": 9.998257709344243e-07, | |
| "loss": 2.4323, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16194331983805668, | |
| "grad_norm": 30.723418441278863, | |
| "learning_rate": 9.937404935870937e-07, | |
| "loss": 2.0558, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.242914979757085, | |
| "grad_norm": 66.03255032436104, | |
| "learning_rate": 9.79064806205334e-07, | |
| "loss": 1.6896, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32388663967611336, | |
| "grad_norm": 58.34439306486902, | |
| "learning_rate": 9.560540456994939e-07, | |
| "loss": 1.5772, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4048582995951417, | |
| "grad_norm": 51.09626482911568, | |
| "learning_rate": 9.251085678648071e-07, | |
| "loss": 1.4404, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48582995951417, | |
| "grad_norm": 33.96795410691758, | |
| "learning_rate": 8.867667817375265e-07, | |
| "loss": 1.329, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5668016194331984, | |
| "grad_norm": 47.3575397280251, | |
| "learning_rate": 8.416957820132741e-07, | |
| "loss": 1.3006, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6477732793522267, | |
| "grad_norm": 111.0994843456021, | |
| "learning_rate": 7.906797425107298e-07, | |
| "loss": 1.2249, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.728744939271255, | |
| "grad_norm": 31.233648257098846, | |
| "learning_rate": 7.346062726185331e-07, | |
| "loss": 1.1918, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8097165991902834, | |
| "grad_norm": 36.495757750998834, | |
| "learning_rate": 6.744509741045834e-07, | |
| "loss": 1.1638, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8906882591093117, | |
| "grad_norm": 31.495305199204555, | |
| "learning_rate": 6.112604669781572e-07, | |
| "loss": 1.1286, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.97165991902834, | |
| "grad_norm": 43.96094961837448, | |
| "learning_rate": 5.46134179731651e-07, | |
| "loss": 1.1919, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.048582995951417, | |
| "grad_norm": 56.72808901425203, | |
| "learning_rate": 4.802052207868654e-07, | |
| "loss": 1.07, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.1295546558704452, | |
| "grad_norm": 31.697978846847704, | |
| "learning_rate": 4.146206639565312e-07, | |
| "loss": 1.084, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.2105263157894737, | |
| "grad_norm": 30.173908854018745, | |
| "learning_rate": 3.5052159092711487e-07, | |
| "loss": 1.0582, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.291497975708502, | |
| "grad_norm": 32.26805588071399, | |
| "learning_rate": 2.8902323799643116e-07, | |
| "loss": 1.0559, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.3724696356275303, | |
| "grad_norm": 33.81653632228646, | |
| "learning_rate": 2.3119559248571125e-07, | |
| "loss": 1.0548, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.4534412955465588, | |
| "grad_norm": 52.76167817194373, | |
| "learning_rate": 1.780447764220422e-07, | |
| "loss": 1.0992, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.5344129554655872, | |
| "grad_norm": 23.30138308406476, | |
| "learning_rate": 1.304955413896705e-07, | |
| "loss": 1.0471, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.6153846153846154, | |
| "grad_norm": 49.57561989321027, | |
| "learning_rate": 8.93751791158432e-08, | |
| "loss": 1.0407, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.6963562753036436, | |
| "grad_norm": 33.34278886124857, | |
| "learning_rate": 5.539912772500943e-08, | |
| "loss": 1.0575, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.777327935222672, | |
| "grad_norm": 34.41441618803528, | |
| "learning_rate": 2.915852409289421e-08, | |
| "loss": 1.0385, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.8582995951417005, | |
| "grad_norm": 35.88999246424493, | |
| "learning_rate": 1.110991887247964e-08, | |
| "loss": 1.0883, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.9392712550607287, | |
| "grad_norm": 38.6094535494541, | |
| "learning_rate": 1.5673331363870169e-09, | |
| "loss": 1.0658, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.9878542510121457, | |
| "step": 246, | |
| "total_flos": 21865739321344.0, | |
| "train_loss": 1.2653712179602645, | |
| "train_runtime": 1757.6372, | |
| "train_samples_per_second": 1.124, | |
| "train_steps_per_second": 0.14 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 246, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 21865739321344.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |