| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9851380042462845, | |
| "eval_steps": 15, | |
| "global_step": 58, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016985138004246284, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016985138004246284, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.9017, | |
| "eval_samples_per_second": 20.401, | |
| "eval_steps_per_second": 5.1, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03397027600849257, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.050955414012738856, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06794055201698514, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08492569002123142, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10191082802547771, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11889596602972399, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13588110403397027, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15286624203821655, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16985138004246284, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18683651804670912, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.20382165605095542, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2208067940552017, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23779193205944799, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.25477707006369427, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.25477707006369427, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.216, | |
| "eval_samples_per_second": 23.719, | |
| "eval_steps_per_second": 5.93, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27176220806794055, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.28874734607218683, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3057324840764331, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3227176220806794, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.33970276008492567, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.35668789808917195, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.37367303609341823, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.39065817409766457, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.40764331210191085, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.42462845010615713, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4416135881104034, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4585987261146497, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.47558386411889597, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.49256900212314225, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5095541401273885, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5095541401273885, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2146, | |
| "eval_samples_per_second": 23.727, | |
| "eval_steps_per_second": 5.932, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5265392781316348, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.2e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5435244161358811, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5605095541401274, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5774946921443737, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5944798301486199, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6114649681528662, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6284501061571125, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6454352441613588, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6624203821656051, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6794055201698513, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6963906581740976, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.2e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7133757961783439, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7303609341825902, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.6e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7473460721868365, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7643312101910829, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7643312101910829, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.2395, | |
| "eval_samples_per_second": 23.588, | |
| "eval_steps_per_second": 5.897, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7813163481953291, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7983014861995754, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8152866242038217, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.832271762208068, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8492569002123143, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8662420382165605, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.8832271762208068, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.9002123142250531, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.9171974522292994, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9341825902335457, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9511677282377919, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.9681528662420382, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.9851380042462845, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 58 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 58, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.245116361388851e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |