| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0034792693534357786, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003865854837150865, | |
| "grad_norm": 2.755742073059082, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1883, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003865854837150865, | |
| "eval_loss": 2.2865633964538574, | |
| "eval_runtime": 53.1931, | |
| "eval_samples_per_second": 20.491, | |
| "eval_steps_per_second": 10.246, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000773170967430173, | |
| "grad_norm": 3.313032388687134, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2499, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011597564511452595, | |
| "grad_norm": 3.1880486011505127, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5334, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011597564511452595, | |
| "eval_loss": 2.2631211280822754, | |
| "eval_runtime": 53.189, | |
| "eval_samples_per_second": 20.493, | |
| "eval_steps_per_second": 10.246, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001546341934860346, | |
| "grad_norm": 2.312131881713867, | |
| "learning_rate": 8e-05, | |
| "loss": 1.962, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0019329274185754324, | |
| "grad_norm": 3.0997703075408936, | |
| "learning_rate": 0.0001, | |
| "loss": 2.003, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002319512902290519, | |
| "grad_norm": 3.679996967315674, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3849, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002319512902290519, | |
| "eval_loss": 1.9262409210205078, | |
| "eval_runtime": 53.2281, | |
| "eval_samples_per_second": 20.478, | |
| "eval_steps_per_second": 10.239, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0027060983860056056, | |
| "grad_norm": 3.800128936767578, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0062, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003092683869720692, | |
| "grad_norm": 3.809640884399414, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8466, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0034792693534357786, | |
| "grad_norm": 9.987689971923828, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6243, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0034792693534357786, | |
| "eval_loss": 1.3205355405807495, | |
| "eval_runtime": 53.2164, | |
| "eval_samples_per_second": 20.482, | |
| "eval_steps_per_second": 10.241, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1847154255593472.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |