| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 200, | |
| "global_step": 44, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.045454545454545456, | |
| "grad_norm": 0.20162349585089198, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8818, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09090909090909091, | |
| "grad_norm": 0.1953500581220745, | |
| "learning_rate": 4e-05, | |
| "loss": 0.876, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13636363636363635, | |
| "grad_norm": 0.5228028889794835, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2233, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.18181818181818182, | |
| "grad_norm": 0.3168539123432193, | |
| "learning_rate": 8e-05, | |
| "loss": 1.019, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22727272727272727, | |
| "grad_norm": 0.2448592330495161, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7696, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2727272727272727, | |
| "grad_norm": 0.5022417968409909, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 0.9575, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3181818181818182, | |
| "grad_norm": 0.3690185930765724, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 0.8849, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 0.3481259765917461, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 0.8554, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4090909090909091, | |
| "grad_norm": 0.2491302807616705, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 0.7842, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.45454545454545453, | |
| "grad_norm": 0.2553944608600153, | |
| "learning_rate": 9.599897218294122e-05, | |
| "loss": 0.7777, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.16006256910442612, | |
| "learning_rate": 9.42728012826605e-05, | |
| "loss": 0.7611, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5454545454545454, | |
| "grad_norm": 0.15558254774359165, | |
| "learning_rate": 9.225950427718975e-05, | |
| "loss": 0.7816, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5909090909090909, | |
| "grad_norm": 0.18832677655086638, | |
| "learning_rate": 8.997213817017507e-05, | |
| "loss": 0.7748, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6363636363636364, | |
| "grad_norm": 0.09681390727181982, | |
| "learning_rate": 8.742553740855506e-05, | |
| "loss": 0.7604, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6818181818181818, | |
| "grad_norm": 0.07979864307427108, | |
| "learning_rate": 8.463621767547998e-05, | |
| "loss": 0.7948, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.0751068874132372, | |
| "learning_rate": 8.162226877976887e-05, | |
| "loss": 0.7387, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7727272727272727, | |
| "grad_norm": 0.09818843566208878, | |
| "learning_rate": 7.840323733655778e-05, | |
| "loss": 0.8671, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8181818181818182, | |
| "grad_norm": 0.12433711342571083, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6836, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8636363636363636, | |
| "grad_norm": 0.09336807665626587, | |
| "learning_rate": 7.143462807015271e-05, | |
| "loss": 0.7574, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.10857087455570018, | |
| "learning_rate": 6.773024435212678e-05, | |
| "loss": 0.6944, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9545454545454546, | |
| "grad_norm": 0.09987180851168877, | |
| "learning_rate": 6.391087319582264e-05, | |
| "loss": 0.7105, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.12403936967122979, | |
| "learning_rate": 6.0001284688802226e-05, | |
| "loss": 0.7271, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0454545454545454, | |
| "grad_norm": 0.11169323633585997, | |
| "learning_rate": 5.602683401276615e-05, | |
| "loss": 0.7422, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0909090909090908, | |
| "grad_norm": 0.08664401280752744, | |
| "learning_rate": 5.201329700547076e-05, | |
| "loss": 0.7493, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1363636363636362, | |
| "grad_norm": 0.08676810328328194, | |
| "learning_rate": 4.798670299452926e-05, | |
| "loss": 0.7524, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1818181818181819, | |
| "grad_norm": 0.08590933006332456, | |
| "learning_rate": 4.397316598723385e-05, | |
| "loss": 0.7569, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2272727272727273, | |
| "grad_norm": 0.08858606445370859, | |
| "learning_rate": 3.9998715311197785e-05, | |
| "loss": 0.74, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2727272727272727, | |
| "grad_norm": 0.07666247259553818, | |
| "learning_rate": 3.608912680417737e-05, | |
| "loss": 0.7329, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3181818181818181, | |
| "grad_norm": 0.07618604122498249, | |
| "learning_rate": 3.226975564787322e-05, | |
| "loss": 0.6354, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3636363636363638, | |
| "grad_norm": 0.08140024777764204, | |
| "learning_rate": 2.8565371929847284e-05, | |
| "loss": 0.686, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4090909090909092, | |
| "grad_norm": 0.08978876050933346, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7447, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 0.0716318283002434, | |
| "learning_rate": 2.1596762663442218e-05, | |
| "loss": 0.679, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.10585147220057532, | |
| "learning_rate": 1.837773122023114e-05, | |
| "loss": 0.716, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.5454545454545454, | |
| "grad_norm": 0.08349343850144146, | |
| "learning_rate": 1.536378232452003e-05, | |
| "loss": 0.7334, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5909090909090908, | |
| "grad_norm": 0.07246804816219393, | |
| "learning_rate": 1.257446259144494e-05, | |
| "loss": 0.684, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6363636363636362, | |
| "grad_norm": 0.08656458135317226, | |
| "learning_rate": 1.0027861829824952e-05, | |
| "loss": 0.7261, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6818181818181817, | |
| "grad_norm": 0.07432309009864736, | |
| "learning_rate": 7.740495722810271e-06, | |
| "loss": 0.7938, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.7272727272727273, | |
| "grad_norm": 0.06644380159937287, | |
| "learning_rate": 5.727198717339511e-06, | |
| "loss": 0.7025, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7727272727272727, | |
| "grad_norm": 0.07589928426253979, | |
| "learning_rate": 4.001027817058789e-06, | |
| "loss": 0.7592, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 0.1400960157888807, | |
| "learning_rate": 2.573177902642726e-06, | |
| "loss": 0.7231, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8636363636363638, | |
| "grad_norm": 0.07387468065399092, | |
| "learning_rate": 1.4529091286973995e-06, | |
| "loss": 0.6872, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.9090909090909092, | |
| "grad_norm": 0.0855342727329305, | |
| "learning_rate": 6.474868681043578e-07, | |
| "loss": 0.696, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.9545454545454546, | |
| "grad_norm": 0.0985088722005277, | |
| "learning_rate": 1.6213459328950352e-07, | |
| "loss": 0.6727, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.07968270308548887, | |
| "learning_rate": 0.0, | |
| "loss": 0.7056, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 44, | |
| "total_flos": 167148584435712.0, | |
| "train_loss": 0.7704400447281924, | |
| "train_runtime": 273.3504, | |
| "train_samples_per_second": 1.266, | |
| "train_steps_per_second": 0.161 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 44, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 167148584435712.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |