| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2987481434330575, | |
| "eval_steps": 32, | |
| "global_step": 176, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001697432633142372, | |
| "eval_loss": 2.4177019596099854, | |
| "eval_runtime": 13.7299, | |
| "eval_samples_per_second": 18.136, | |
| "eval_steps_per_second": 18.136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008487163165711862, | |
| "grad_norm": 0.5580189228057861, | |
| "learning_rate": 5e-06, | |
| "loss": 2.0835, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016974326331423723, | |
| "grad_norm": 0.5617932081222534, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3638, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025461489497135583, | |
| "grad_norm": 0.637174129486084, | |
| "learning_rate": 9.99743108100344e-06, | |
| "loss": 2.3443, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033948652662847446, | |
| "grad_norm": 0.7906777858734131, | |
| "learning_rate": 9.989726963751683e-06, | |
| "loss": 2.4875, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.042435815828559306, | |
| "grad_norm": 0.7220119833946228, | |
| "learning_rate": 9.976895564745993e-06, | |
| "loss": 2.2905, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.050922978994271166, | |
| "grad_norm": 0.4569860100746155, | |
| "learning_rate": 9.95895006911623e-06, | |
| "loss": 2.8207, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05431784426055591, | |
| "eval_loss": 2.396263599395752, | |
| "eval_runtime": 13.7534, | |
| "eval_samples_per_second": 18.105, | |
| "eval_steps_per_second": 18.105, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.059410142159983026, | |
| "grad_norm": 0.5562223196029663, | |
| "learning_rate": 9.935908917072253e-06, | |
| "loss": 2.3774, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06789730532569489, | |
| "grad_norm": 0.8851813077926636, | |
| "learning_rate": 9.907795784955327e-06, | |
| "loss": 2.3059, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07638446849140675, | |
| "grad_norm": 0.8263425827026367, | |
| "learning_rate": 9.874639560909118e-06, | |
| "loss": 2.2858, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08487163165711861, | |
| "grad_norm": 0.9496198296546936, | |
| "learning_rate": 9.836474315195148e-06, | |
| "loss": 2.2606, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09335879482283047, | |
| "grad_norm": 0.8389888405799866, | |
| "learning_rate": 9.793339265183303e-06, | |
| "loss": 2.4757, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.10184595798854233, | |
| "grad_norm": 0.9090803861618042, | |
| "learning_rate": 9.745278735053345e-06, | |
| "loss": 2.2428, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10863568852111181, | |
| "eval_loss": 2.3315982818603516, | |
| "eval_runtime": 13.995, | |
| "eval_samples_per_second": 17.792, | |
| "eval_steps_per_second": 17.792, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.11033312115425419, | |
| "grad_norm": 0.8944710493087769, | |
| "learning_rate": 9.692342110248802e-06, | |
| "loss": 2.361, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.11882028431996605, | |
| "grad_norm": 0.8705277442932129, | |
| "learning_rate": 9.63458378673011e-06, | |
| "loss": 2.2061, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1273074474856779, | |
| "grad_norm": 1.0183981657028198, | |
| "learning_rate": 9.572063115079063e-06, | |
| "loss": 2.3014, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13579461065138979, | |
| "grad_norm": 0.9694010615348816, | |
| "learning_rate": 9.504844339512096e-06, | |
| "loss": 2.4273, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14428177381710164, | |
| "grad_norm": 0.6600094437599182, | |
| "learning_rate": 9.432996531865001e-06, | |
| "loss": 2.2039, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.1527689369828135, | |
| "grad_norm": 1.437016487121582, | |
| "learning_rate": 9.356593520616948e-06, | |
| "loss": 2.4129, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16125610014852534, | |
| "grad_norm": 1.1358604431152344, | |
| "learning_rate": 9.275713815026732e-06, | |
| "loss": 2.2346, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.16295353278166771, | |
| "eval_loss": 2.2801592350006104, | |
| "eval_runtime": 14.3531, | |
| "eval_samples_per_second": 17.348, | |
| "eval_steps_per_second": 17.348, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.16974326331423722, | |
| "grad_norm": 0.8347494006156921, | |
| "learning_rate": 9.190440524459203e-06, | |
| "loss": 2.5003, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17823042647994908, | |
| "grad_norm": 0.9528422355651855, | |
| "learning_rate": 9.10086127298478e-06, | |
| "loss": 2.2398, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.18671758964566093, | |
| "grad_norm": 0.7451781630516052, | |
| "learning_rate": 9.007068109339783e-06, | |
| "loss": 2.253, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1952047528113728, | |
| "grad_norm": 0.6891763210296631, | |
| "learning_rate": 8.90915741234015e-06, | |
| "loss": 2.0703, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.20369191597708466, | |
| "grad_norm": 0.7363041639328003, | |
| "learning_rate": 8.807229791845673e-06, | |
| "loss": 2.3083, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21217907914279652, | |
| "grad_norm": 0.7747501730918884, | |
| "learning_rate": 8.701389985376578e-06, | |
| "loss": 2.2058, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.21727137704222363, | |
| "eval_loss": 2.245945692062378, | |
| "eval_runtime": 14.3131, | |
| "eval_samples_per_second": 17.397, | |
| "eval_steps_per_second": 17.397, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.22066624230850837, | |
| "grad_norm": 0.8016952276229858, | |
| "learning_rate": 8.591746750488639e-06, | |
| "loss": 2.1023, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.22915340547422025, | |
| "grad_norm": 1.4869773387908936, | |
| "learning_rate": 8.478412753017433e-06, | |
| "loss": 2.2433, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.2376405686399321, | |
| "grad_norm": 1.111100673675537, | |
| "learning_rate": 8.361504451306585e-06, | |
| "loss": 2.0758, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24612773180564396, | |
| "grad_norm": 0.7958012819290161, | |
| "learning_rate": 8.241141976538944e-06, | |
| "loss": 2.1178, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.2546148949713558, | |
| "grad_norm": 0.6610277891159058, | |
| "learning_rate": 8.117449009293668e-06, | |
| "loss": 2.0289, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.26310205813706766, | |
| "grad_norm": 0.9238812923431396, | |
| "learning_rate": 7.99055265245608e-06, | |
| "loss": 2.3871, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.27158922130277957, | |
| "grad_norm": 0.9540156126022339, | |
| "learning_rate": 7.860583300610849e-06, | |
| "loss": 2.069, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.27158922130277957, | |
| "eval_loss": 2.2213292121887207, | |
| "eval_runtime": 14.5462, | |
| "eval_samples_per_second": 17.118, | |
| "eval_steps_per_second": 17.118, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2800763844684914, | |
| "grad_norm": 1.1984089612960815, | |
| "learning_rate": 7.727674506052744e-06, | |
| "loss": 1.9745, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.2885635476342033, | |
| "grad_norm": 0.8632123470306396, | |
| "learning_rate": 7.591962841552627e-06, | |
| "loss": 1.9814, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.29705071079991513, | |
| "grad_norm": 0.6884729266166687, | |
| "learning_rate": 7.453587760019691e-06, | |
| "loss": 2.1216, | |
| "step": 175 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 16, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5596099588915200.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |