| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 444, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.512305457368493, |
| "epoch": 0.05638567803777841, |
| "grad_norm": 0.052001953125, |
| "learning_rate": 0.00019973322836635518, |
| "loss": 1.5421083068847656, |
| "mean_token_accuracy": 0.6486250500380993, |
| "num_tokens": 144508.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.2983414649218321, |
| "epoch": 0.11277135607555681, |
| "grad_norm": 0.12451171875, |
| "learning_rate": 0.00019674836970574254, |
| "loss": 1.2756206512451171, |
| "mean_token_accuracy": 0.7112903011217714, |
| "num_tokens": 292109.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.0407171499356627, |
| "epoch": 0.16915703411333521, |
| "grad_norm": 0.1474609375, |
| "learning_rate": 0.00019054482374931467, |
| "loss": 1.0164385223388672, |
| "mean_token_accuracy": 0.7733419627696275, |
| "num_tokens": 446139.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 0.7892182947043329, |
| "epoch": 0.22554271215111363, |
| "grad_norm": 0.1201171875, |
| "learning_rate": 0.00018132897407355657, |
| "loss": 0.7477215576171875, |
| "mean_token_accuracy": 0.82292207069695, |
| "num_tokens": 591284.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.7213720260327682, |
| "epoch": 0.28192839018889204, |
| "grad_norm": 0.1103515625, |
| "learning_rate": 0.0001694074195220634, |
| "loss": 0.683692398071289, |
| "mean_token_accuracy": 0.846045880690217, |
| "num_tokens": 741747.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 0.6420099837053567, |
| "epoch": 0.33831406822667043, |
| "grad_norm": 0.146484375, |
| "learning_rate": 0.0001551767740770446, |
| "loss": 0.6045019912719727, |
| "mean_token_accuracy": 0.8612289320677519, |
| "num_tokens": 888467.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.4919711536122486, |
| "epoch": 0.3946997462644488, |
| "grad_norm": 0.04248046875, |
| "learning_rate": 0.0001391104720490156, |
| "loss": 0.4492445755004883, |
| "mean_token_accuracy": 0.8903629670292139, |
| "num_tokens": 1036757.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 0.5750386103335768, |
| "epoch": 0.45108542430222726, |
| "grad_norm": 0.06689453125, |
| "learning_rate": 0.00012174301755815571, |
| "loss": 0.5542393112182618, |
| "mean_token_accuracy": 0.8759176962077617, |
| "num_tokens": 1181945.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.5648965935781598, |
| "epoch": 0.5074711023400056, |
| "grad_norm": 0.03857421875, |
| "learning_rate": 0.0001036522023057659, |
| "loss": 0.547780876159668, |
| "mean_token_accuracy": 0.8807101232558489, |
| "num_tokens": 1335419.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 0.4930458738701418, |
| "epoch": 0.5638567803777841, |
| "grad_norm": 0.06494140625, |
| "learning_rate": 8.543988322649954e-05, |
| "loss": 0.47976242065429686, |
| "mean_token_accuracy": 0.8966810719668865, |
| "num_tokens": 1479342.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.34622532883193347, |
| "epoch": 0.6202424584155625, |
| "grad_norm": 0.0869140625, |
| "learning_rate": 6.77119595228554e-05, |
| "loss": 0.32271854400634764, |
| "mean_token_accuracy": 0.9300810437649488, |
| "num_tokens": 1629061.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 0.39914618858136236, |
| "epoch": 0.6766281364533409, |
| "grad_norm": 0.07177734375, |
| "learning_rate": 5.105821521889147e-05, |
| "loss": 0.3532614898681641, |
| "mean_token_accuracy": 0.9161469136178494, |
| "num_tokens": 1772842.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.39773431999608877, |
| "epoch": 0.7330138144911192, |
| "grad_norm": 0.06689453125, |
| "learning_rate": 3.60326978441109e-05, |
| "loss": 0.40174495697021484, |
| "mean_token_accuracy": 0.9162117794901132, |
| "num_tokens": 1923761.0, |
| "step": 325 |
| }, |
| { |
| "entropy": 0.3905838479846716, |
| "epoch": 0.7893994925288976, |
| "grad_norm": 0.05859375, |
| "learning_rate": 2.3135286022146785e-05, |
| "loss": 0.3990034484863281, |
| "mean_token_accuracy": 0.923584694750607, |
| "num_tokens": 2071111.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.38003566025290636, |
| "epoch": 0.845785170566676, |
| "grad_norm": 0.0546875, |
| "learning_rate": 1.2795059185619229e-05, |
| "loss": 0.3592890930175781, |
| "mean_token_accuracy": 0.9243136387318373, |
| "num_tokens": 2218689.0, |
| "step": 375 |
| }, |
| { |
| "entropy": 0.41276534273289145, |
| "epoch": 0.9021708486044545, |
| "grad_norm": 0.0693359375, |
| "learning_rate": 5.3560226842390596e-06, |
| "loss": 0.38957675933837893, |
| "mean_token_accuracy": 0.9158677716553211, |
| "num_tokens": 2362130.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.31493653893470763, |
| "epoch": 0.9585565266422329, |
| "grad_norm": 0.0361328125, |
| "learning_rate": 1.0656631924889749e-06, |
| "loss": 0.29476009368896483, |
| "mean_token_accuracy": 0.9362043110281228, |
| "num_tokens": 2511099.0, |
| "step": 425 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 444, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1175526982295245e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
