| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013420567018956551, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00268411340379131, | |
| "grad_norm": 0.9448651671409607, | |
| "learning_rate": 1e-05, | |
| "loss": 2.519, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00268411340379131, | |
| "eval_loss": 2.568769693374634, | |
| "eval_runtime": 110.3368, | |
| "eval_samples_per_second": 5.692, | |
| "eval_steps_per_second": 2.846, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00536822680758262, | |
| "grad_norm": 1.0865734815597534, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2466, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00536822680758262, | |
| "eval_loss": 2.555813789367676, | |
| "eval_runtime": 68.2166, | |
| "eval_samples_per_second": 9.206, | |
| "eval_steps_per_second": 4.603, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00805234021137393, | |
| "grad_norm": 1.0192607641220093, | |
| "learning_rate": 3e-05, | |
| "loss": 2.4755, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01073645361516524, | |
| "grad_norm": 0.992130696773529, | |
| "learning_rate": 4e-05, | |
| "loss": 2.3809, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01073645361516524, | |
| "eval_loss": 2.5295355319976807, | |
| "eval_runtime": 68.5814, | |
| "eval_samples_per_second": 9.157, | |
| "eval_steps_per_second": 4.579, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013420567018956551, | |
| "grad_norm": 1.1429316997528076, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4975, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3822182832537600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |