| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2491506228765572, | |
| "eval_steps": 55, | |
| "global_step": 55, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004530011325028313, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004530011325028313, | |
| "eval_loss": NaN, | |
| "eval_runtime": 17.5744, | |
| "eval_samples_per_second": 21.167, | |
| "eval_steps_per_second": 5.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009060022650056626, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013590033975084938, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01812004530011325, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022650056625141562, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027180067950169876, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.031710079275198186, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0362400906002265, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04077010192525481, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.045300113250283124, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04983012457531144, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05436013590033975, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05889014722536806, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06342015855039637, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06795016987542468, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.072480181200453, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07701019252548132, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08154020385050963, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08607021517553794, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09060022650056625, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09513023782559456, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09966024915062288, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10419026047565119, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1087202718006795, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11325028312570781, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11778029445073612, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2000000000000004e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12231030577576443, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4000000000000005e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12684031710079274, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6000000000000006e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13137032842582105, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13590033975084936, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1404303510758777, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.2e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.144960362400906, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.14949037372593432, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15402038505096263, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.15855039637599094, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16308040770101925, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16761041902604756, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.4e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17214043035107587, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.6e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17667044167610418, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1812004530011325, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1857304643261608, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.2e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19026047565118911, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.4e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.19479048697621745, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.6e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.19932049830124576, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.800000000000001e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.20385050962627407, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20838052095130238, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.200000000000001e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2129105322763307, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.4e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.217440543601359, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.6e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22197055492638731, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22650056625141562, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23103057757644394, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999146252290264e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.23556058890147225, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.996585300715116e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.24009060022650056, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99231801983717e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.24462061155152887, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.986345866928941e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2491506228765572, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.978670881475172e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2491506228765572, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.9373, | |
| "eval_samples_per_second": 21.963, | |
| "eval_steps_per_second": 5.491, | |
| "step": 55 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 220, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 55, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7930497309081600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |