| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09017132551848513, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018034265103697023, | |
| "eval_loss": 1.5323797464370728, | |
| "eval_runtime": 15.1257, | |
| "eval_samples_per_second": 15.47, | |
| "eval_steps_per_second": 7.735, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009017132551848512, | |
| "grad_norm": 8.786983489990234, | |
| "learning_rate": 5e-05, | |
| "loss": 6.1675, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.018034265103697024, | |
| "grad_norm": 7.997146129608154, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5276, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018034265103697024, | |
| "eval_loss": 1.2454485893249512, | |
| "eval_runtime": 15.4977, | |
| "eval_samples_per_second": 15.099, | |
| "eval_steps_per_second": 7.55, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027051397655545536, | |
| "grad_norm": 6.936639308929443, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.7001, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03606853020739405, | |
| "grad_norm": 6.008756160736084, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.1918, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03606853020739405, | |
| "eval_loss": 1.0457502603530884, | |
| "eval_runtime": 15.539, | |
| "eval_samples_per_second": 15.059, | |
| "eval_steps_per_second": 7.529, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04508566275924256, | |
| "grad_norm": 6.224257469177246, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.0398, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05410279531109107, | |
| "grad_norm": 5.880407333374023, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0062, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05410279531109107, | |
| "eval_loss": 0.9842478036880493, | |
| "eval_runtime": 15.7977, | |
| "eval_samples_per_second": 14.812, | |
| "eval_steps_per_second": 7.406, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06311992786293959, | |
| "grad_norm": 6.333781719207764, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.9598, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0721370604147881, | |
| "grad_norm": 5.879536151885986, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.7936, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0721370604147881, | |
| "eval_loss": 0.9594914317131042, | |
| "eval_runtime": 15.5315, | |
| "eval_samples_per_second": 15.066, | |
| "eval_steps_per_second": 7.533, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0811541929666366, | |
| "grad_norm": 6.407863616943359, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.7838, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09017132551848513, | |
| "grad_norm": 6.500133514404297, | |
| "learning_rate": 0.0, | |
| "loss": 3.6373, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09017132551848513, | |
| "eval_loss": 0.9541807174682617, | |
| "eval_runtime": 15.4078, | |
| "eval_samples_per_second": 15.187, | |
| "eval_steps_per_second": 7.594, | |
| "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": 8894809381011456.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |