| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.21551724137931033, | |
| "eval_steps": 3, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008620689655172414, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008620689655172414, | |
| "eval_loss": NaN, | |
| "eval_runtime": 10.497, | |
| "eval_samples_per_second": 14.004, | |
| "eval_steps_per_second": 3.525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017241379310344827, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02586206896551724, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.953429730181653e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02586206896551724, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.9353, | |
| "eval_samples_per_second": 14.796, | |
| "eval_steps_per_second": 3.724, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.034482758620689655, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.814586436738998e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04310344827586207, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.586056507527266e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05172413793103448, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.272097022732443e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05172413793103448, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.9371, | |
| "eval_samples_per_second": 14.793, | |
| "eval_steps_per_second": 3.723, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0603448275862069, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.8785564535221e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06896551724137931, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.412765716093272e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07758620689655173, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.883401610574336e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07758620689655173, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.9373, | |
| "eval_samples_per_second": 14.793, | |
| "eval_steps_per_second": 3.723, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08620689655172414, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.300325188655761e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09482758620689655, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.674398060854931e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10344827586206896, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.01728006526317e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10344827586206896, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.9574, | |
| "eval_samples_per_second": 14.763, | |
| "eval_steps_per_second": 3.716, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11206896551724138, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.341212066823355e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1206896551724138, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.658787933176646e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12931034482758622, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.982719934736832e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12931034482758622, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.901, | |
| "eval_samples_per_second": 14.847, | |
| "eval_steps_per_second": 3.737, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13793103448275862, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.325601939145069e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14655172413793102, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6996748113442394e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15517241379310345, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1165983894256647e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15517241379310345, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.9101, | |
| "eval_samples_per_second": 14.833, | |
| "eval_steps_per_second": 3.734, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16379310344827586, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5872342839067306e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1214435464779006e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1810344827586207, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2790297726755716e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1810344827586207, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.924, | |
| "eval_samples_per_second": 14.813, | |
| "eval_steps_per_second": 3.728, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1896551724137931, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.139434924727359e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19827586206896552, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8541356326100433e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6570269818346224e-07, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20689655172413793, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.9123, | |
| "eval_samples_per_second": 14.83, | |
| "eval_steps_per_second": 3.733, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21551724137931033, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5014484246528e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |