| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007974481658692184, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001594896331738437, | |
| "eval_loss": 1.199280023574829, | |
| "eval_runtime": 225.5899, | |
| "eval_samples_per_second": 11.703, | |
| "eval_steps_per_second": 5.851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007974481658692185, | |
| "grad_norm": 0.43941763043403625, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2094, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001594896331738437, | |
| "grad_norm": 0.3336985409259796, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1356, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001594896331738437, | |
| "eval_loss": 1.15956711769104, | |
| "eval_runtime": 232.8327, | |
| "eval_samples_per_second": 11.339, | |
| "eval_steps_per_second": 5.669, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023923444976076554, | |
| "grad_norm": 0.4425758719444275, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1819, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003189792663476874, | |
| "grad_norm": 0.593981921672821, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0736, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003189792663476874, | |
| "eval_loss": 1.065757155418396, | |
| "eval_runtime": 232.901, | |
| "eval_samples_per_second": 11.335, | |
| "eval_steps_per_second": 5.668, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003987240829346092, | |
| "grad_norm": 0.3362281918525696, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.115, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004784688995215311, | |
| "grad_norm": 0.4011121690273285, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0856, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004784688995215311, | |
| "eval_loss": 1.0489628314971924, | |
| "eval_runtime": 232.9203, | |
| "eval_samples_per_second": 11.334, | |
| "eval_steps_per_second": 5.667, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005582137161084529, | |
| "grad_norm": 0.4398060441017151, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0603, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "grad_norm": 0.5486422777175903, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0651, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "eval_loss": 1.0430271625518799, | |
| "eval_runtime": 232.8498, | |
| "eval_samples_per_second": 11.338, | |
| "eval_steps_per_second": 5.669, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007177033492822967, | |
| "grad_norm": 0.3932763338088989, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0669, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007974481658692184, | |
| "grad_norm": 0.3477610945701599, | |
| "learning_rate": 0.0, | |
| "loss": 0.9524, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007974481658692184, | |
| "eval_loss": 1.0419983863830566, | |
| "eval_runtime": 232.7443, | |
| "eval_samples_per_second": 11.343, | |
| "eval_steps_per_second": 5.671, | |
| "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": 9039468904316928.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |