| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0024904739371902473, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.9809478743804945e-05, | |
| "eval_loss": 1.2049556970596313, | |
| "eval_runtime": 268.8732, | |
| "eval_samples_per_second": 31.442, | |
| "eval_steps_per_second": 15.721, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00024904739371902474, | |
| "grad_norm": 1.1703884601593018, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9729, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004980947874380495, | |
| "grad_norm": 1.128602385520935, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2574, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004980947874380495, | |
| "eval_loss": 1.1664738655090332, | |
| "eval_runtime": 268.8172, | |
| "eval_samples_per_second": 31.449, | |
| "eval_steps_per_second": 15.724, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007471421811570742, | |
| "grad_norm": 1.5504509210586548, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.0723, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000996189574876099, | |
| "grad_norm": 1.3867547512054443, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1504, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000996189574876099, | |
| "eval_loss": 1.0666918754577637, | |
| "eval_runtime": 267.8435, | |
| "eval_samples_per_second": 31.563, | |
| "eval_steps_per_second": 15.782, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012452369685951236, | |
| "grad_norm": 1.2634857892990112, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1064, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014942843623141483, | |
| "grad_norm": 1.7904630899429321, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1542, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0014942843623141483, | |
| "eval_loss": 1.041231632232666, | |
| "eval_runtime": 269.0737, | |
| "eval_samples_per_second": 31.419, | |
| "eval_steps_per_second": 15.709, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001743331756033173, | |
| "grad_norm": 1.4260520935058594, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0855, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.001992379149752198, | |
| "grad_norm": 1.1240558624267578, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9091, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001992379149752198, | |
| "eval_loss": 1.030592918395996, | |
| "eval_runtime": 267.7805, | |
| "eval_samples_per_second": 31.571, | |
| "eval_steps_per_second": 15.785, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0022414265434712224, | |
| "grad_norm": 1.029605507850647, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8889, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0024904739371902473, | |
| "grad_norm": 1.431504487991333, | |
| "learning_rate": 0.0, | |
| "loss": 0.9654, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0024904739371902473, | |
| "eval_loss": 1.0290184020996094, | |
| "eval_runtime": 268.4739, | |
| "eval_samples_per_second": 31.489, | |
| "eval_steps_per_second": 15.745, | |
| "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": 1310933888532480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |