| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003713813529422688, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.427627058845375e-05, | |
| "eval_loss": 1.8039292097091675, | |
| "eval_runtime": 466.504, | |
| "eval_samples_per_second": 12.152, | |
| "eval_steps_per_second": 6.077, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003713813529422688, | |
| "grad_norm": 15.996868133544922, | |
| "learning_rate": 5e-05, | |
| "loss": 7.2598, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007427627058845376, | |
| "grad_norm": 10.017637252807617, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7789, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007427627058845376, | |
| "eval_loss": 1.5627775192260742, | |
| "eval_runtime": 468.537, | |
| "eval_samples_per_second": 12.099, | |
| "eval_steps_per_second": 6.051, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011141440588268063, | |
| "grad_norm": 10.058262825012207, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.0454, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0014855254117690751, | |
| "grad_norm": 13.010249137878418, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.9304, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014855254117690751, | |
| "eval_loss": 1.4773796796798706, | |
| "eval_runtime": 467.8787, | |
| "eval_samples_per_second": 12.116, | |
| "eval_steps_per_second": 6.059, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001856906764711344, | |
| "grad_norm": 8.150615692138672, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.0852, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022282881176536127, | |
| "grad_norm": 10.96812915802002, | |
| "learning_rate": 5e-05, | |
| "loss": 5.6197, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022282881176536127, | |
| "eval_loss": 1.431856632232666, | |
| "eval_runtime": 468.2349, | |
| "eval_samples_per_second": 12.107, | |
| "eval_steps_per_second": 6.055, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0025996694705958815, | |
| "grad_norm": 9.371012687683105, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.7799, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0029710508235381503, | |
| "grad_norm": 7.734054088592529, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.64, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0029710508235381503, | |
| "eval_loss": 1.4109234809875488, | |
| "eval_runtime": 468.0726, | |
| "eval_samples_per_second": 12.111, | |
| "eval_steps_per_second": 6.057, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003342432176480419, | |
| "grad_norm": 7.80369758605957, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.5457, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003713813529422688, | |
| "grad_norm": 7.892637252807617, | |
| "learning_rate": 0.0, | |
| "loss": 5.5715, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003713813529422688, | |
| "eval_loss": 1.4075946807861328, | |
| "eval_runtime": 467.6847, | |
| "eval_samples_per_second": 12.121, | |
| "eval_steps_per_second": 6.062, | |
| "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": 1.1874351439675392e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |