| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015037593984962405, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005012531328320802, | |
| "eval_loss": 1.1545190811157227, | |
| "eval_runtime": 74.7335, | |
| "eval_samples_per_second": 11.253, | |
| "eval_steps_per_second": 5.633, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015037593984962407, | |
| "grad_norm": 14.427947998046875, | |
| "learning_rate": 6e-05, | |
| "loss": 4.5286, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0030075187969924814, | |
| "grad_norm": 8.940759658813477, | |
| "learning_rate": 0.00012, | |
| "loss": 4.4594, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0040100250626566416, | |
| "eval_loss": 0.9068899750709534, | |
| "eval_runtime": 74.1327, | |
| "eval_samples_per_second": 11.345, | |
| "eval_steps_per_second": 5.679, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004511278195488722, | |
| "grad_norm": 4.615734100341797, | |
| "learning_rate": 0.00018, | |
| "loss": 3.3499, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006015037593984963, | |
| "grad_norm": 4.977766036987305, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 3.2685, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007518796992481203, | |
| "grad_norm": 5.421140670776367, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.538, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008020050125313283, | |
| "eval_loss": 0.8385846018791199, | |
| "eval_runtime": 74.4233, | |
| "eval_samples_per_second": 11.3, | |
| "eval_steps_per_second": 5.657, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009022556390977444, | |
| "grad_norm": 6.071444034576416, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.5141, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010526315789473684, | |
| "grad_norm": 7.219034194946289, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 3.5675, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012030075187969926, | |
| "grad_norm": 4.945723533630371, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 3.3491, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012030075187969926, | |
| "eval_loss": 0.8206897377967834, | |
| "eval_runtime": 74.5024, | |
| "eval_samples_per_second": 11.288, | |
| "eval_steps_per_second": 5.651, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013533834586466165, | |
| "grad_norm": 6.191557884216309, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.6754, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015037593984962405, | |
| "grad_norm": 4.54865837097168, | |
| "learning_rate": 0.0, | |
| "loss": 3.6574, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0898513470685184e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |