| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003469301022576476, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.469301022576476e-05, | |
| "grad_norm": 0.028307748958468437, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3795, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.469301022576476e-05, | |
| "eval_loss": 10.378649711608887, | |
| "eval_runtime": 140.9358, | |
| "eval_samples_per_second": 86.117, | |
| "eval_steps_per_second": 43.062, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.938602045152952e-05, | |
| "grad_norm": 0.03619663044810295, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3766, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010407903067729429, | |
| "grad_norm": 0.03194531798362732, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3807, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010407903067729429, | |
| "eval_loss": 10.37862777709961, | |
| "eval_runtime": 142.5808, | |
| "eval_samples_per_second": 85.124, | |
| "eval_steps_per_second": 42.565, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013877204090305905, | |
| "grad_norm": 0.02971941977739334, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3796, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001734650511288238, | |
| "grad_norm": 0.033148981630802155, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3795, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020815806135458857, | |
| "grad_norm": 0.024479001760482788, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3799, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00020815806135458857, | |
| "eval_loss": 10.378538131713867, | |
| "eval_runtime": 142.1577, | |
| "eval_samples_per_second": 85.377, | |
| "eval_steps_per_second": 42.692, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00024285107158035334, | |
| "grad_norm": 0.028492305427789688, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3797, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002775440818061181, | |
| "grad_norm": 0.032648127526044846, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3809, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00031223709203188286, | |
| "grad_norm": 0.018097268417477608, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3802, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00031223709203188286, | |
| "eval_loss": 10.378382682800293, | |
| "eval_runtime": 142.2823, | |
| "eval_samples_per_second": 85.302, | |
| "eval_steps_per_second": 42.655, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003469301022576476, | |
| "grad_norm": 0.028453005477786064, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3748, | |
| "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": 1046048931840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |