| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.7242524916943522, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 16.070100784301758, | |
| "learning_rate": 5e-05, | |
| "loss": 4.8852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "eval_loss": 4.792490005493164, | |
| "eval_runtime": 0.7317, | |
| "eval_samples_per_second": 68.332, | |
| "eval_steps_per_second": 17.766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10631229235880399, | |
| "grad_norm": 15.72305965423584, | |
| "learning_rate": 0.0001, | |
| "loss": 4.6739, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15946843853820597, | |
| "grad_norm": 14.131994247436523, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 4.3832, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21262458471760798, | |
| "grad_norm": 16.100086212158203, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.2328, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "grad_norm": 9.526208877563477, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.0447, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31893687707641194, | |
| "grad_norm": 6.778939723968506, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.0156, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 3.811636209487915, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.6336, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.42524916943521596, | |
| "grad_norm": 4.02534294128418, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4985, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.47840531561461797, | |
| "grad_norm": 3.899996280670166, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.4257, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.53156146179402, | |
| "grad_norm": 2.4773781299591064, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.2646, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.584717607973422, | |
| "grad_norm": 1.6356959342956543, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.2353, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6378737541528239, | |
| "grad_norm": 1.855863332748413, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.1652, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6910299003322259, | |
| "grad_norm": 1.7059516906738281, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.1623, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7441860465116279, | |
| "grad_norm": 3.5583112239837646, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.2193, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7973421926910299, | |
| "grad_norm": 2.0394420623779297, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1814, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8504983388704319, | |
| "grad_norm": 2.178466558456421, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1836, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9036544850498339, | |
| "grad_norm": 2.2939162254333496, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.2283, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9568106312292359, | |
| "grad_norm": 1.9878804683685303, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.1923, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.043189368770764, | |
| "grad_norm": 8.555853843688965, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.5503, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0963455149501662, | |
| "grad_norm": 1.7653311491012573, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.0921, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.149501661129568, | |
| "grad_norm": 0.7832552790641785, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.0621, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2026578073089702, | |
| "grad_norm": 0.47030219435691833, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.0903, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.255813953488372, | |
| "grad_norm": 1.1789742708206177, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.1346, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.308970099667774, | |
| "grad_norm": 1.045068621635437, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.126, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3621262458471761, | |
| "grad_norm": 0.8990850448608398, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.1019, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3621262458471761, | |
| "eval_loss": 0.12839345633983612, | |
| "eval_runtime": 0.7402, | |
| "eval_samples_per_second": 67.551, | |
| "eval_steps_per_second": 17.563, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.415282392026578, | |
| "grad_norm": 0.7274023294448853, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0638, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4684385382059801, | |
| "grad_norm": 1.0477628707885742, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.1032, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.521594684385382, | |
| "grad_norm": 1.7702083587646484, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.0773, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.574750830564784, | |
| "grad_norm": 0.9557569026947021, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.0616, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.627906976744186, | |
| "grad_norm": 1.0757166147232056, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1396, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6810631229235882, | |
| "grad_norm": 0.8739386796951294, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0655, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.73421926910299, | |
| "grad_norm": 0.9457898736000061, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.0842, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.787375415282392, | |
| "grad_norm": 0.5630450248718262, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0476, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.8405315614617939, | |
| "grad_norm": 0.7644055485725403, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.1071, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.893687707641196, | |
| "grad_norm": 1.1439839601516724, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.1219, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.946843853820598, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.1116, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.0332225913621262, | |
| "grad_norm": 1.7485463619232178, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.1243, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.086378737541528, | |
| "grad_norm": 0.47398442029953003, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0464, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.13953488372093, | |
| "grad_norm": 0.9993898272514343, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.082, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.1926910299003324, | |
| "grad_norm": 0.46211889386177063, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0404, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.2458471760797343, | |
| "grad_norm": 0.8578104972839355, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.1049, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.299003322259136, | |
| "grad_norm": 0.7607599496841431, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.086, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.352159468438538, | |
| "grad_norm": 0.46289491653442383, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0477, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.4053156146179404, | |
| "grad_norm": 0.8016815185546875, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.0811, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.4584717607973423, | |
| "grad_norm": 0.43612438440322876, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0495, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.511627906976744, | |
| "grad_norm": 0.7244629263877869, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0904, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.564784053156146, | |
| "grad_norm": 0.526421844959259, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0517, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.617940199335548, | |
| "grad_norm": 0.7599980235099792, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0553, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.6710963455149503, | |
| "grad_norm": 0.7634601593017578, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0647, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.7242524916943522, | |
| "grad_norm": 0.7769803404808044, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1012, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.7242524916943522, | |
| "eval_loss": 0.14976823329925537, | |
| "eval_runtime": 0.725, | |
| "eval_samples_per_second": 68.97, | |
| "eval_steps_per_second": 17.932, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.54445405339648e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |