| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003865854837150865, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003865854837150865, | |
| "grad_norm": 2.704545736312866, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1883, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003865854837150865, | |
| "eval_loss": 2.2865633964538574, | |
| "eval_runtime": 52.0586, | |
| "eval_samples_per_second": 20.938, | |
| "eval_steps_per_second": 10.469, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000773170967430173, | |
| "grad_norm": 3.247318744659424, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2499, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011597564511452595, | |
| "grad_norm": 3.147203207015991, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5355, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011597564511452595, | |
| "eval_loss": 2.2640984058380127, | |
| "eval_runtime": 52.1071, | |
| "eval_samples_per_second": 20.918, | |
| "eval_steps_per_second": 10.459, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001546341934860346, | |
| "grad_norm": 2.2698464393615723, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9615, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0019329274185754324, | |
| "grad_norm": 2.997138261795044, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0052, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002319512902290519, | |
| "grad_norm": 3.600839614868164, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3884, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002319512902290519, | |
| "eval_loss": 1.9305282831192017, | |
| "eval_runtime": 52.1727, | |
| "eval_samples_per_second": 20.892, | |
| "eval_steps_per_second": 10.446, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0027060983860056056, | |
| "grad_norm": 3.755431652069092, | |
| "learning_rate": 0.00014, | |
| "loss": 2.0119, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003092683869720692, | |
| "grad_norm": 3.74912166595459, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8548, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0034792693534357786, | |
| "grad_norm": 9.68393325805664, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6276, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0034792693534357786, | |
| "eval_loss": 1.3230209350585938, | |
| "eval_runtime": 52.1736, | |
| "eval_samples_per_second": 20.892, | |
| "eval_steps_per_second": 10.446, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003865854837150865, | |
| "grad_norm": 2.7541391849517822, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2777, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2052393617326080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |