| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8205128205128205, |
| "eval_steps": 500, |
| "global_step": 120, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.9341673284769059, |
| "epoch": 0.06837606837606838, |
| "grad_norm": 1.2578125, |
| "learning_rate": 2.7750000000000004e-05, |
| "loss": 1.8236064910888672, |
| "mean_token_accuracy": 0.6031250022351742, |
| "num_tokens": 81920.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.5755251368507743, |
| "epoch": 0.13675213675213677, |
| "grad_norm": 0.306640625, |
| "learning_rate": 2.525e-05, |
| "loss": 0.3169667959213257, |
| "mean_token_accuracy": 0.9330759823322297, |
| "num_tokens": 163840.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.03900249442085624, |
| "epoch": 0.20512820512820512, |
| "grad_norm": 0.0284423828125, |
| "learning_rate": 2.275e-05, |
| "loss": 0.0061474073678255085, |
| "mean_token_accuracy": 1.0, |
| "num_tokens": 245760.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.013878341647796333, |
| "epoch": 0.27350427350427353, |
| "grad_norm": 0.01019287109375, |
| "learning_rate": 2.025e-05, |
| "loss": 0.001719124987721443, |
| "mean_token_accuracy": 1.0, |
| "num_tokens": 327680.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.007600244274362922, |
| "epoch": 0.3418803418803419, |
| "grad_norm": 0.005950927734375, |
| "learning_rate": 1.775e-05, |
| "loss": 0.0008654000237584114, |
| "mean_token_accuracy": 1.0, |
| "num_tokens": 409600.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.005724262841977179, |
| "epoch": 0.41025641025641024, |
| "grad_norm": 0.00482177734375, |
| "learning_rate": 1.525e-05, |
| "loss": 0.0006292078644037247, |
| "mean_token_accuracy": 1.0, |
| "num_tokens": 491520.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.005162813549395651, |
| "epoch": 0.47863247863247865, |
| "grad_norm": 0.00439453125, |
| "learning_rate": 1.275e-05, |
| "loss": 0.0005607008002698422, |
| "mean_token_accuracy": 1.0, |
| "num_tokens": 573440.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.004928319191094488, |
| "epoch": 0.5470085470085471, |
| "grad_norm": 0.00421142578125, |
| "learning_rate": 1.025e-05, |
| "loss": 0.0005334688816219568, |
| "mean_token_accuracy": 1.0, |
| "num_tokens": 655360.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.00477353862952441, |
| "epoch": 0.6153846153846154, |
| "grad_norm": 0.004150390625, |
| "learning_rate": 7.75e-06, |
| "loss": 0.0005137024912983179, |
| "mean_token_accuracy": 1.0, |
| "num_tokens": 737280.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.004704260791186243, |
| "epoch": 0.6837606837606838, |
| "grad_norm": 0.0040283203125, |
| "learning_rate": 5.25e-06, |
| "loss": 0.0005053752567619086, |
| "mean_token_accuracy": 1.0, |
| "num_tokens": 819200.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.004669400909915566, |
| "epoch": 0.7521367521367521, |
| "grad_norm": 0.0040283203125, |
| "learning_rate": 2.75e-06, |
| "loss": 0.0005010279826819896, |
| "mean_token_accuracy": 1.0, |
| "num_tokens": 901120.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.004655064782127738, |
| "epoch": 0.8205128205128205, |
| "grad_norm": 0.00396728515625, |
| "learning_rate": 2.5e-07, |
| "loss": 0.0004998001269996167, |
| "mean_token_accuracy": 1.0, |
| "num_tokens": 983040.0, |
| "step": 120 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 120, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 120, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8228571017379840.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
