| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 4, |
| "global_step": 23, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.043478260869565216, |
| "grad_norm": 0.18782003223896027, |
| "learning_rate": 0.0, |
| "loss": 1.727783203125, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.08695652173913043, |
| "grad_norm": 0.22847582399845123, |
| "learning_rate": 5e-05, |
| "loss": 1.745361328125, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.13043478260869565, |
| "grad_norm": 0.19071611762046814, |
| "learning_rate": 4.977098244232099e-05, |
| "loss": 1.720703125, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.17391304347826086, |
| "grad_norm": 0.19614891707897186, |
| "learning_rate": 4.90885919063262e-05, |
| "loss": 1.69091796875, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.21739130434782608, |
| "grad_norm": 0.21143198013305664, |
| "learning_rate": 4.796671989547667e-05, |
| "loss": 1.564453125, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2608695652173913, |
| "grad_norm": 0.0746946781873703, |
| "learning_rate": 4.6428204488701576e-05, |
| "loss": 0.671875, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.30434782608695654, |
| "grad_norm": 0.17559966444969177, |
| "learning_rate": 4.450436542297082e-05, |
| "loss": 1.45751953125, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.30434782608695654, |
| "eval_loss": 1.2763671875, |
| "eval_runtime": 5.828, |
| "eval_samples_per_second": 0.686, |
| "eval_steps_per_second": 0.172, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.34782608695652173, |
| "grad_norm": 0.17109356820583344, |
| "learning_rate": 4.223436651376892e-05, |
| "loss": 1.490234375, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.391304347826087, |
| "grad_norm": 0.6726886630058289, |
| "learning_rate": 3.966441839275095e-05, |
| "loss": 0.9942626953125, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 0.12483895570039749, |
| "learning_rate": 3.6846837792542446e-05, |
| "loss": 1.384033203125, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.4782608695652174, |
| "grad_norm": 0.12765726447105408, |
| "learning_rate": 3.383898252893217e-05, |
| "loss": 1.37548828125, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.4782608695652174, |
| "eval_loss": 1.216796875, |
| "eval_runtime": 5.7998, |
| "eval_samples_per_second": 0.69, |
| "eval_steps_per_second": 0.172, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5217391304347826, |
| "grad_norm": 0.12192913889884949, |
| "learning_rate": 3.070208386114892e-05, |
| "loss": 1.34033203125, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5652173913043478, |
| "grad_norm": 0.11237656325101852, |
| "learning_rate": 2.7500000000000004e-05, |
| "loss": 1.315185546875, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6086956521739131, |
| "grad_norm": 0.12283302843570709, |
| "learning_rate": 2.429791613885109e-05, |
| "loss": 1.434326171875, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6521739130434783, |
| "grad_norm": 0.13110016286373138, |
| "learning_rate": 2.1161017471067835e-05, |
| "loss": 1.374755859375, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6521739130434783, |
| "eval_loss": 1.19677734375, |
| "eval_runtime": 5.8081, |
| "eval_samples_per_second": 0.689, |
| "eval_steps_per_second": 0.172, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.6956521739130435, |
| "grad_norm": 0.12423460930585861, |
| "learning_rate": 1.815316220745756e-05, |
| "loss": 1.42333984375, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.7391304347826086, |
| "grad_norm": 0.11869314312934875, |
| "learning_rate": 1.5335581607249064e-05, |
| "loss": 1.456298828125, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.782608695652174, |
| "grad_norm": 0.11196423321962357, |
| "learning_rate": 1.2765633486231088e-05, |
| "loss": 1.33642578125, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8260869565217391, |
| "grad_norm": 0.1125522181391716, |
| "learning_rate": 1.0495634577029192e-05, |
| "loss": 1.41162109375, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.8260869565217391, |
| "eval_loss": 1.1875, |
| "eval_runtime": 5.8123, |
| "eval_samples_per_second": 0.688, |
| "eval_steps_per_second": 0.172, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 0.10117685049772263, |
| "learning_rate": 8.571795511298423e-06, |
| "loss": 1.38818359375, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9130434782608695, |
| "grad_norm": 0.11501135677099228, |
| "learning_rate": 7.033280104523337e-06, |
| "loss": 1.3525390625, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.9565217391304348, |
| "grad_norm": 0.12201500684022903, |
| "learning_rate": 5.911408093673812e-06, |
| "loss": 1.329345703125, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.1027703657746315, |
| "learning_rate": 5.229017557679016e-06, |
| "loss": 1.360595703125, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.18359375, |
| "eval_runtime": 5.7934, |
| "eval_samples_per_second": 0.69, |
| "eval_steps_per_second": 0.173, |
| "step": 23 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 23, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.74515885224362e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
