| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06749915626054674, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013499831252109348, | |
| "eval_loss": 4.265491008758545, | |
| "eval_runtime": 285.8199, | |
| "eval_samples_per_second": 4.366, | |
| "eval_steps_per_second": 0.546, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004049949375632805, | |
| "grad_norm": 35.99859619140625, | |
| "learning_rate": 3e-05, | |
| "loss": 17.0135, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006749915626054675, | |
| "eval_loss": 3.8347327709198, | |
| "eval_runtime": 287.9169, | |
| "eval_samples_per_second": 4.335, | |
| "eval_steps_per_second": 0.542, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00809989875126561, | |
| "grad_norm": 14.753717422485352, | |
| "learning_rate": 6e-05, | |
| "loss": 16.8055, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012149848126898413, | |
| "grad_norm": 19.439973831176758, | |
| "learning_rate": 9e-05, | |
| "loss": 15.2762, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01349983125210935, | |
| "eval_loss": 2.515470027923584, | |
| "eval_runtime": 287.8629, | |
| "eval_samples_per_second": 4.335, | |
| "eval_steps_per_second": 0.542, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01619979750253122, | |
| "grad_norm": 12.475789070129395, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 10.8456, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020249746878164023, | |
| "grad_norm": 11.72419261932373, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 8.899, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020249746878164023, | |
| "eval_loss": 1.7485647201538086, | |
| "eval_runtime": 287.8964, | |
| "eval_samples_per_second": 4.335, | |
| "eval_steps_per_second": 0.542, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024299696253796826, | |
| "grad_norm": 11.490859985351562, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 6.2954, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0269996625042187, | |
| "eval_loss": 1.2927414178848267, | |
| "eval_runtime": 287.7942, | |
| "eval_samples_per_second": 4.336, | |
| "eval_steps_per_second": 0.542, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028349645629429633, | |
| "grad_norm": 9.176210403442383, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 5.5427, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03239959500506244, | |
| "grad_norm": 11.53584098815918, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 5.5624, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03374957813027337, | |
| "eval_loss": 1.104496955871582, | |
| "eval_runtime": 287.8974, | |
| "eval_samples_per_second": 4.335, | |
| "eval_steps_per_second": 0.542, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03644954438069524, | |
| "grad_norm": 7.262444019317627, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 4.614, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.040499493756328046, | |
| "grad_norm": 7.796113014221191, | |
| "learning_rate": 5e-05, | |
| "loss": 4.012, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.040499493756328046, | |
| "eval_loss": 1.0315279960632324, | |
| "eval_runtime": 287.8886, | |
| "eval_samples_per_second": 4.335, | |
| "eval_steps_per_second": 0.542, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04454944313196085, | |
| "grad_norm": 8.100488662719727, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 3.6741, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04724940938238272, | |
| "eval_loss": 0.9920565485954285, | |
| "eval_runtime": 287.864, | |
| "eval_samples_per_second": 4.335, | |
| "eval_steps_per_second": 0.542, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04859939250759365, | |
| "grad_norm": 4.739097595214844, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 3.6449, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05264934188322646, | |
| "grad_norm": 5.869235038757324, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 3.446, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0539993250084374, | |
| "eval_loss": 0.9727193117141724, | |
| "eval_runtime": 287.775, | |
| "eval_samples_per_second": 4.337, | |
| "eval_steps_per_second": 0.542, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.056699291258859266, | |
| "grad_norm": 6.903482913970947, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 3.9028, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.060749240634492066, | |
| "grad_norm": 10.054128646850586, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.0095, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.060749240634492066, | |
| "eval_loss": 0.9632046222686768, | |
| "eval_runtime": 287.8144, | |
| "eval_samples_per_second": 4.336, | |
| "eval_steps_per_second": 0.542, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06479919001012488, | |
| "grad_norm": 9.620219230651855, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 4.6745, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06749915626054674, | |
| "eval_loss": 0.9605395197868347, | |
| "eval_runtime": 287.8877, | |
| "eval_samples_per_second": 4.335, | |
| "eval_steps_per_second": 0.542, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3038984859798733e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |