| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13966480446927373, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002793296089385475, | |
| "eval_loss": 2.4049742221832275, | |
| "eval_runtime": 13.2901, | |
| "eval_samples_per_second": 11.362, | |
| "eval_steps_per_second": 5.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013966480446927373, | |
| "grad_norm": 2.8598062992095947, | |
| "learning_rate": 5e-05, | |
| "loss": 9.1267, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027932960893854747, | |
| "grad_norm": 4.437131881713867, | |
| "learning_rate": 0.0001, | |
| "loss": 8.7871, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027932960893854747, | |
| "eval_loss": 2.1106879711151123, | |
| "eval_runtime": 12.4419, | |
| "eval_samples_per_second": 12.136, | |
| "eval_steps_per_second": 6.108, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04189944134078212, | |
| "grad_norm": 3.954702854156494, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 7.7161, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.055865921787709494, | |
| "grad_norm": 4.341027736663818, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.666, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.055865921787709494, | |
| "eval_loss": 1.68687903881073, | |
| "eval_runtime": 12.5323, | |
| "eval_samples_per_second": 12.049, | |
| "eval_steps_per_second": 6.064, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06983240223463687, | |
| "grad_norm": 4.4329705238342285, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.7389, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08379888268156424, | |
| "grad_norm": 4.825051307678223, | |
| "learning_rate": 5e-05, | |
| "loss": 6.4153, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08379888268156424, | |
| "eval_loss": 1.5849660634994507, | |
| "eval_runtime": 12.6209, | |
| "eval_samples_per_second": 11.964, | |
| "eval_steps_per_second": 6.022, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09776536312849161, | |
| "grad_norm": 4.308661937713623, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.0258, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11173184357541899, | |
| "grad_norm": 4.541212558746338, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.8698, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11173184357541899, | |
| "eval_loss": 1.5316410064697266, | |
| "eval_runtime": 12.7421, | |
| "eval_samples_per_second": 11.85, | |
| "eval_steps_per_second": 5.964, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12569832402234637, | |
| "grad_norm": 5.563971996307373, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.0079, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13966480446927373, | |
| "grad_norm": 4.291133403778076, | |
| "learning_rate": 0.0, | |
| "loss": 6.0674, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13966480446927373, | |
| "eval_loss": 1.521949052810669, | |
| "eval_runtime": 12.6138, | |
| "eval_samples_per_second": 11.971, | |
| "eval_steps_per_second": 6.025, | |
| "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": 1.4264026791936e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |