| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.22727272727272727, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022727272727272728, | |
| "grad_norm": 6.847477436065674, | |
| "learning_rate": 2e-05, | |
| "loss": 3.638, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022727272727272728, | |
| "eval_loss": 3.789806842803955, | |
| "eval_runtime": 1.2259, | |
| "eval_samples_per_second": 60.364, | |
| "eval_steps_per_second": 8.157, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 5.260680198669434, | |
| "learning_rate": 4e-05, | |
| "loss": 3.4007, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06818181818181818, | |
| "grad_norm": 6.062076091766357, | |
| "learning_rate": 6e-05, | |
| "loss": 3.5331, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06818181818181818, | |
| "eval_loss": 3.6856677532196045, | |
| "eval_runtime": 1.219, | |
| "eval_samples_per_second": 60.704, | |
| "eval_steps_per_second": 8.203, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 6.924163341522217, | |
| "learning_rate": 8e-05, | |
| "loss": 3.2663, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11363636363636363, | |
| "grad_norm": 5.1875200271606445, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6316, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 5.6750168800354, | |
| "learning_rate": 0.00012, | |
| "loss": 2.8824, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "eval_loss": 2.815485715866089, | |
| "eval_runtime": 1.2233, | |
| "eval_samples_per_second": 60.492, | |
| "eval_steps_per_second": 8.175, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1590909090909091, | |
| "grad_norm": 4.6825079917907715, | |
| "learning_rate": 0.00014, | |
| "loss": 2.9952, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 4.181937217712402, | |
| "learning_rate": 0.00016, | |
| "loss": 2.3997, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20454545454545456, | |
| "grad_norm": 3.558675765991211, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8518, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20454545454545456, | |
| "eval_loss": 1.6439586877822876, | |
| "eval_runtime": 1.2232, | |
| "eval_samples_per_second": 60.497, | |
| "eval_steps_per_second": 8.175, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 3.013317108154297, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6307, | |
| "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": 8234950176276480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |