| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5555555555555556, | |
| "eval_steps": 20, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009259259259259259, | |
| "eval_loss": 2.1662161350250244, | |
| "eval_runtime": 31.2323, | |
| "eval_samples_per_second": 48.059, | |
| "eval_steps_per_second": 6.019, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09259259259259259, | |
| "grad_norm": 2.140625, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.8573, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "grad_norm": 1.5390625, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.8314, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18518518518518517, | |
| "eval_loss": 1.7036446332931519, | |
| "eval_runtime": 27.1456, | |
| "eval_samples_per_second": 55.294, | |
| "eval_steps_per_second": 6.926, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 1.765625, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8651, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 1.5390625, | |
| "learning_rate": 0.00019984815164333163, | |
| "loss": 1.9748, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "eval_loss": 1.8448469638824463, | |
| "eval_runtime": 42.3761, | |
| "eval_samples_per_second": 35.421, | |
| "eval_steps_per_second": 4.436, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.46296296296296297, | |
| "grad_norm": 1.25, | |
| "learning_rate": 0.00019939306773179497, | |
| "loss": 2.0039, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 1.25, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 2.0413, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "eval_loss": 1.89992094039917, | |
| "eval_runtime": 42.6851, | |
| "eval_samples_per_second": 35.164, | |
| "eval_steps_per_second": 4.404, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 600, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.897208656730522e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |