| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02932121389825539, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005864242779651077, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005864242779651077, | |
| "eval_loss": NaN, | |
| "eval_runtime": 23.658, | |
| "eval_samples_per_second": 30.349, | |
| "eval_steps_per_second": 15.175, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011728485559302155, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017592728338953233, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002345697111860431, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002932121389825539, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0035185456677906467, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004104969945755754, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004691394223720862, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00527781850168597, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005864242779651078, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0064506670576161855, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007037091335581293, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007623515613546401, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007623515613546401, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.6472, | |
| "eval_samples_per_second": 31.704, | |
| "eval_steps_per_second": 15.852, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008209939891511508, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008796364169476616, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009382788447441724, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009969212725406832, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01055563700337194, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011142061281337047, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011728485559302155, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012314909837267263, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012901334115232371, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.013487758393197479, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014074182671162587, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014660606949127694, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015247031227092802, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.015247031227092802, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.6583, | |
| "eval_samples_per_second": 31.688, | |
| "eval_steps_per_second": 15.844, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01583345550505791, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.016419879783023016, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.017006304060988124, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.017592728338953232, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01817915261691834, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.018765576894883448, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.019352001172848556, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.019938425450813663, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02052484972877877, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02111127400674388, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.021697698284708987, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.022284122562674095, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.022870546840639203, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.022870546840639203, | |
| "eval_loss": NaN, | |
| "eval_runtime": 22.6084, | |
| "eval_samples_per_second": 31.758, | |
| "eval_steps_per_second": 15.879, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02345697111860431, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02404339539656942, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.989850859999227e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.024629819674534526, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.025216243952499634, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.025802668230464742, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7248368952908053e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02638909250842985, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026975516786394958, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2235870926211619e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.027561941064360065, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.907519900580861e-07, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.028148365342325173, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02873478962029028, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.706665667180091e-08, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02932121389825539, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9289160535834624.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |