| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05877366487708392, | |
| "eval_steps": 13, | |
| "global_step": 52, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011302627860977678, | |
| "eval_loss": 0.7253943681716919, | |
| "eval_runtime": 222.5674, | |
| "eval_samples_per_second": 6.695, | |
| "eval_steps_per_second": 0.84, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003390788358293303, | |
| "grad_norm": 6.4600725173950195, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.9057, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006781576716586606, | |
| "grad_norm": 4.287564277648926, | |
| "learning_rate": 3e-05, | |
| "loss": 2.7228, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010172365074879909, | |
| "grad_norm": 4.434852600097656, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.2412, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013563153433173212, | |
| "grad_norm": 4.096804618835449, | |
| "learning_rate": 4.997482666353287e-05, | |
| "loss": 1.6976, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01469341621927098, | |
| "eval_loss": 0.281572163105011, | |
| "eval_runtime": 224.6256, | |
| "eval_samples_per_second": 6.633, | |
| "eval_steps_per_second": 0.832, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016953941791466517, | |
| "grad_norm": 3.934027910232544, | |
| "learning_rate": 4.984280524733107e-05, | |
| "loss": 1.2107, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020344730149759818, | |
| "grad_norm": 2.3636763095855713, | |
| "learning_rate": 4.959823971496574e-05, | |
| "loss": 0.8397, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02373551850805312, | |
| "grad_norm": 1.3671884536743164, | |
| "learning_rate": 4.9242238009417175e-05, | |
| "loss": 0.7578, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.027126306866346424, | |
| "grad_norm": 1.3218061923980713, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.6645, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02938683243854196, | |
| "eval_loss": 0.16004851460456848, | |
| "eval_runtime": 224.8305, | |
| "eval_samples_per_second": 6.627, | |
| "eval_steps_per_second": 0.832, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.030517095224639728, | |
| "grad_norm": 1.757283091545105, | |
| "learning_rate": 4.820287471297598e-05, | |
| "loss": 0.6531, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.033907883582933035, | |
| "grad_norm": 1.2630192041397095, | |
| "learning_rate": 4.752422169756048e-05, | |
| "loss": 0.616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03729867194122634, | |
| "grad_norm": 1.2325754165649414, | |
| "learning_rate": 4.674352832889239e-05, | |
| "loss": 0.6141, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.040689460299519635, | |
| "grad_norm": 1.5199618339538574, | |
| "learning_rate": 4.586433134303257e-05, | |
| "loss": 0.6026, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04408024865781294, | |
| "grad_norm": 1.2060375213623047, | |
| "learning_rate": 4.489061372204453e-05, | |
| "loss": 0.6114, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04408024865781294, | |
| "eval_loss": 0.14285726845264435, | |
| "eval_runtime": 224.8051, | |
| "eval_samples_per_second": 6.628, | |
| "eval_steps_per_second": 0.832, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04747103701610624, | |
| "grad_norm": 1.2959660291671753, | |
| "learning_rate": 4.382678665009028e-05, | |
| "loss": 0.576, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.050861825374399545, | |
| "grad_norm": 1.1517972946166992, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.5597, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05425261373269285, | |
| "grad_norm": 1.2231593132019043, | |
| "learning_rate": 4.144846814849282e-05, | |
| "loss": 0.5803, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05764340209098615, | |
| "grad_norm": 1.1372201442718506, | |
| "learning_rate": 4.01447510960205e-05, | |
| "loss": 0.5299, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.05877366487708392, | |
| "eval_loss": 0.13713335990905762, | |
| "eval_runtime": 224.8683, | |
| "eval_samples_per_second": 6.626, | |
| "eval_steps_per_second": 0.832, | |
| "step": 52 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 150, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.462511032294441e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |