| { | |
| "best_metric": 6.0121965408325195, | |
| "best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained_last/de_mlm/de_childes_42/checkpoint-12000", | |
| "epoch": 9.0123920390537, | |
| "eval_steps": 2000, | |
| "global_step": 12000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.5020653398422832, | |
| "eval_loss": 7.505205154418945, | |
| "eval_runtime": 4.9012, | |
| "eval_samples_per_second": 677.383, | |
| "eval_steps_per_second": 42.438, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.0041306796845664, | |
| "grad_norm": 1.3569484949111938, | |
| "learning_rate": 1e-05, | |
| "loss": 7.4063, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.0041306796845664, | |
| "eval_loss": 6.433775901794434, | |
| "eval_runtime": 4.7916, | |
| "eval_samples_per_second": 692.873, | |
| "eval_steps_per_second": 43.409, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.50619601952685, | |
| "eval_loss": 6.305135250091553, | |
| "eval_runtime": 4.8722, | |
| "eval_samples_per_second": 681.421, | |
| "eval_steps_per_second": 42.691, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.008261359369133, | |
| "grad_norm": 1.548327088356018, | |
| "learning_rate": 2e-05, | |
| "loss": 6.0672, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 6.008261359369133, | |
| "eval_loss": 6.1662516593933105, | |
| "eval_runtime": 4.8572, | |
| "eval_samples_per_second": 683.527, | |
| "eval_steps_per_second": 42.823, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 7.510326699211416, | |
| "eval_loss": 6.095215797424316, | |
| "eval_runtime": 4.7932, | |
| "eval_samples_per_second": 692.655, | |
| "eval_steps_per_second": 43.395, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 9.0123920390537, | |
| "grad_norm": 1.639375925064087, | |
| "learning_rate": 3e-05, | |
| "loss": 5.8691, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 9.0123920390537, | |
| "eval_loss": 6.0121965408325195, | |
| "eval_runtime": 4.8217, | |
| "eval_samples_per_second": 688.56, | |
| "eval_steps_per_second": 43.139, | |
| "step": 12000 | |
| } | |
| ], | |
| "logging_steps": 4000, | |
| "max_steps": 100000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 76, | |
| "save_steps": 4000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3742538301702144.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |