| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 415, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.060350030175015085, | |
| "grad_norm": 0.31135597825050354, | |
| "learning_rate": 8.18181818181818e-05, | |
| "loss": 1.9235, | |
| "mean_token_accuracy": 0.6165974247455597, | |
| "num_tokens": 157030.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12070006035003017, | |
| "grad_norm": 0.32249024510383606, | |
| "learning_rate": 0.00016704545454545452, | |
| "loss": 1.0538, | |
| "mean_token_accuracy": 0.7450298243761062, | |
| "num_tokens": 284204.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18105009052504525, | |
| "grad_norm": 0.3015844523906708, | |
| "learning_rate": 0.0002522727272727273, | |
| "loss": 0.6726, | |
| "mean_token_accuracy": 0.8188469475507736, | |
| "num_tokens": 441659.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.24140012070006034, | |
| "grad_norm": 0.5104885697364807, | |
| "learning_rate": 0.0002999887132933212, | |
| "loss": 0.5348, | |
| "mean_token_accuracy": 0.8504667854309083, | |
| "num_tokens": 567533.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.30175015087507545, | |
| "grad_norm": 0.278422474861145, | |
| "learning_rate": 0.0002998791256978121, | |
| "loss": 0.4144, | |
| "mean_token_accuracy": 0.8816475421190262, | |
| "num_tokens": 725296.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.3621001810500905, | |
| "grad_norm": 0.35799795389175415, | |
| "learning_rate": 0.0002996530399366737, | |
| "loss": 0.3693, | |
| "mean_token_accuracy": 0.8962992638349533, | |
| "num_tokens": 851708.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.4224502112251056, | |
| "grad_norm": 0.2955951690673828, | |
| "learning_rate": 0.00029931063174202567, | |
| "loss": 0.2746, | |
| "mean_token_accuracy": 0.921732594370842, | |
| "num_tokens": 1008739.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4828002414001207, | |
| "grad_norm": 0.3763117790222168, | |
| "learning_rate": 0.00029885216726118104, | |
| "loss": 0.2386, | |
| "mean_token_accuracy": 0.9305408012866974, | |
| "num_tokens": 1134832.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5431502715751357, | |
| "grad_norm": 0.3240911066532135, | |
| "learning_rate": 0.00029827800284977474, | |
| "loss": 0.1885, | |
| "mean_token_accuracy": 0.9465595126152039, | |
| "num_tokens": 1293095.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.6035003017501509, | |
| "grad_norm": 0.3682485520839691, | |
| "learning_rate": 0.00029758858479477575, | |
| "loss": 0.1832, | |
| "mean_token_accuracy": 0.9486982274055481, | |
| "num_tokens": 1419060.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.663850331925166, | |
| "grad_norm": 0.29996615648269653, | |
| "learning_rate": 0.0002967844489675963, | |
| "loss": 0.1501, | |
| "mean_token_accuracy": 0.9576406496763229, | |
| "num_tokens": 1577978.0, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.724200362100181, | |
| "grad_norm": 0.3568132221698761, | |
| "learning_rate": 0.00029586622040756957, | |
| "loss": 0.1246, | |
| "mean_token_accuracy": 0.964940841794014, | |
| "num_tokens": 1705052.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.7845503922751962, | |
| "grad_norm": 0.258465439081192, | |
| "learning_rate": 0.0002948346128361186, | |
| "loss": 0.1089, | |
| "mean_token_accuracy": 0.970317553281784, | |
| "num_tokens": 1861669.0, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.8449004224502112, | |
| "grad_norm": 0.3066297173500061, | |
| "learning_rate": 0.00029369042810199416, | |
| "loss": 0.1072, | |
| "mean_token_accuracy": 0.9702006059885026, | |
| "num_tokens": 1988735.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.9052504526252263, | |
| "grad_norm": 0.22371642291545868, | |
| "learning_rate": 0.0002924345555580135, | |
| "loss": 0.1117, | |
| "mean_token_accuracy": 0.9696371680498124, | |
| "num_tokens": 2146989.0, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.9656004828002414, | |
| "grad_norm": 0.4630758762359619, | |
| "learning_rate": 0.000291067971369783, | |
| "loss": 0.0863, | |
| "mean_token_accuracy": 0.9765483093261719, | |
| "num_tokens": 2274615.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.09050165861845016, | |
| "eval_mean_token_accuracy": 0.9750120665576006, | |
| "eval_num_tokens": 2354180.0, | |
| "eval_runtime": 61.8103, | |
| "eval_samples_per_second": 5.97, | |
| "eval_steps_per_second": 2.993, | |
| "step": 415 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 2905, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0113122195121254e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |