| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0429000429000429, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000858000858000858, | |
| "eval_loss": 2.572244882583618, | |
| "eval_runtime": 13.9828, | |
| "eval_samples_per_second": 35.114, | |
| "eval_steps_per_second": 17.593, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00429000429000429, | |
| "grad_norm": 0.9092069864273071, | |
| "learning_rate": 5e-05, | |
| "loss": 2.626, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00858000858000858, | |
| "grad_norm": 0.6895273327827454, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4413, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00858000858000858, | |
| "eval_loss": 2.5162887573242188, | |
| "eval_runtime": 13.8733, | |
| "eval_samples_per_second": 35.392, | |
| "eval_steps_per_second": 17.732, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01287001287001287, | |
| "grad_norm": 1.0629734992980957, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5554, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01716001716001716, | |
| "grad_norm": 1.5819611549377441, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01716001716001716, | |
| "eval_loss": 2.406935453414917, | |
| "eval_runtime": 13.8288, | |
| "eval_samples_per_second": 35.506, | |
| "eval_steps_per_second": 17.789, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02145002145002145, | |
| "grad_norm": 1.3351898193359375, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4197, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02574002574002574, | |
| "grad_norm": 1.1603292226791382, | |
| "learning_rate": 5e-05, | |
| "loss": 2.434, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02574002574002574, | |
| "eval_loss": 2.365774393081665, | |
| "eval_runtime": 13.9497, | |
| "eval_samples_per_second": 35.198, | |
| "eval_steps_per_second": 17.635, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03003003003003003, | |
| "grad_norm": 1.5101451873779297, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.4102, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03432003432003432, | |
| "grad_norm": 1.228721022605896, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03432003432003432, | |
| "eval_loss": 2.349761486053467, | |
| "eval_runtime": 14.0476, | |
| "eval_samples_per_second": 34.953, | |
| "eval_steps_per_second": 17.512, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03861003861003861, | |
| "grad_norm": 1.2431485652923584, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.4303, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0429000429000429, | |
| "grad_norm": 1.1994407176971436, | |
| "learning_rate": 0.0, | |
| "loss": 2.3418, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0429000429000429, | |
| "eval_loss": 2.347376823425293, | |
| "eval_runtime": 13.813, | |
| "eval_samples_per_second": 35.546, | |
| "eval_steps_per_second": 17.809, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1244823042392064.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |