| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.7058823529411766, | |
| "eval_steps": 500, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.5514968283268096, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.103, | |
| "mean_token_accuracy": 0.6410358250141144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.5564948741796076, | |
| "learning_rate": 0.0001955572805786141, | |
| "loss": 1.95, | |
| "mean_token_accuracy": 0.6562966406345367, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.2298309803009033, | |
| "eval_mean_token_accuracy": 0.6953375414013863, | |
| "eval_runtime": 1.1412, | |
| "eval_samples_per_second": 4.381, | |
| "eval_steps_per_second": 0.876, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.1176470588235294, | |
| "grad_norm": 0.3550428109424067, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.5318, | |
| "mean_token_accuracy": 0.6940737068653107, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.7058823529411766, | |
| "grad_norm": 0.15172839418805506, | |
| "learning_rate": 7.774790660436858e-05, | |
| "loss": 1.4025, | |
| "mean_token_accuracy": 0.7238408386707306, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.040649652481079, | |
| "eval_mean_token_accuracy": 0.6979705393314362, | |
| "eval_runtime": 1.278, | |
| "eval_samples_per_second": 3.912, | |
| "eval_steps_per_second": 0.782, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 2.235294117647059, | |
| "grad_norm": 0.16155482865148485, | |
| "learning_rate": 1.7376122568400532e-05, | |
| "loss": 1.4263, | |
| "mean_token_accuracy": 0.7188252657651901, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "eval_loss": 2.0348782539367676, | |
| "eval_mean_token_accuracy": 0.710096988413069, | |
| "eval_runtime": 1.278, | |
| "eval_samples_per_second": 3.912, | |
| "eval_steps_per_second": 0.782, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.7058823529411766, | |
| "step": 24, | |
| "total_flos": 7336072979677184.0, | |
| "train_loss": 1.5557562708854675, | |
| "train_runtime": 102.3381, | |
| "train_samples_per_second": 1.935, | |
| "train_steps_per_second": 0.235 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 24, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7336072979677184.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |