| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.2967032967032967, |
| "eval_steps": 500, |
| "global_step": 45, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.006593406593406593, |
| "grad_norm": 0.8349836468696594, |
| "learning_rate": 0.0, |
| "loss": 0.9434, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.013186813186813187, |
| "grad_norm": 0.8700987696647644, |
| "learning_rate": 4e-05, |
| "loss": 0.9905, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01978021978021978, |
| "grad_norm": 0.9241365194320679, |
| "learning_rate": 8e-05, |
| "loss": 0.9438, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.026373626373626374, |
| "grad_norm": 0.9019892811775208, |
| "learning_rate": 0.00012, |
| "loss": 0.9216, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.03296703296703297, |
| "grad_norm": 0.8872910141944885, |
| "learning_rate": 0.00016, |
| "loss": 0.9374, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03956043956043956, |
| "grad_norm": 0.5874530076980591, |
| "learning_rate": 0.0002, |
| "loss": 0.7673, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.046153846153846156, |
| "grad_norm": 0.5062956809997559, |
| "learning_rate": 0.00019955654101995565, |
| "loss": 0.8011, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.05274725274725275, |
| "grad_norm": 0.5953829288482666, |
| "learning_rate": 0.00019911308203991133, |
| "loss": 0.8455, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05934065934065934, |
| "grad_norm": 0.5616072416305542, |
| "learning_rate": 0.00019866962305986697, |
| "loss": 0.8265, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.06593406593406594, |
| "grad_norm": 0.49180087447166443, |
| "learning_rate": 0.00019822616407982261, |
| "loss": 0.8561, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07252747252747253, |
| "grad_norm": 0.42030951380729675, |
| "learning_rate": 0.00019778270509977829, |
| "loss": 0.8796, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07912087912087912, |
| "grad_norm": 0.3004567325115204, |
| "learning_rate": 0.00019733924611973393, |
| "loss": 0.8636, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 0.2698984444141388, |
| "learning_rate": 0.0001968957871396896, |
| "loss": 0.718, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.09230769230769231, |
| "grad_norm": 0.25445133447647095, |
| "learning_rate": 0.00019645232815964525, |
| "loss": 0.7235, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.0989010989010989, |
| "grad_norm": 0.22418756783008575, |
| "learning_rate": 0.00019600886917960092, |
| "loss": 0.688, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.1054945054945055, |
| "grad_norm": 0.2096303105354309, |
| "learning_rate": 0.00019556541019955653, |
| "loss": 0.7267, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.11208791208791209, |
| "grad_norm": 0.3029191195964813, |
| "learning_rate": 0.0001951219512195122, |
| "loss": 0.7763, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.11868131868131868, |
| "grad_norm": 0.2644464075565338, |
| "learning_rate": 0.00019467849223946785, |
| "loss": 0.7618, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.12527472527472527, |
| "grad_norm": 0.2536560893058777, |
| "learning_rate": 0.00019423503325942352, |
| "loss": 0.7999, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.13186813186813187, |
| "grad_norm": 0.24718916416168213, |
| "learning_rate": 0.00019379157427937917, |
| "loss": 0.752, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13846153846153847, |
| "grad_norm": 0.2625150680541992, |
| "learning_rate": 0.00019334811529933484, |
| "loss": 0.736, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.14505494505494507, |
| "grad_norm": 0.32164040207862854, |
| "learning_rate": 0.00019290465631929045, |
| "loss": 0.7043, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.15164835164835164, |
| "grad_norm": 0.3981449604034424, |
| "learning_rate": 0.00019246119733924613, |
| "loss": 0.7057, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.15824175824175823, |
| "grad_norm": 0.3817313015460968, |
| "learning_rate": 0.00019201773835920177, |
| "loss": 0.7413, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.16483516483516483, |
| "grad_norm": 0.29256680607795715, |
| "learning_rate": 0.00019157427937915744, |
| "loss": 0.693, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 0.27523350715637207, |
| "learning_rate": 0.00019113082039911309, |
| "loss": 0.6474, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.17802197802197803, |
| "grad_norm": 0.23511967062950134, |
| "learning_rate": 0.00019068736141906876, |
| "loss": 0.6519, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.18461538461538463, |
| "grad_norm": 0.2961374819278717, |
| "learning_rate": 0.0001902439024390244, |
| "loss": 0.6426, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.1912087912087912, |
| "grad_norm": 0.2760772407054901, |
| "learning_rate": 0.00018980044345898005, |
| "loss": 0.7388, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1978021978021978, |
| "grad_norm": 0.2285313606262207, |
| "learning_rate": 0.00018935698447893572, |
| "loss": 0.7756, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2043956043956044, |
| "grad_norm": 0.2657061517238617, |
| "learning_rate": 0.00018891352549889136, |
| "loss": 0.7275, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.210989010989011, |
| "grad_norm": 0.22572828829288483, |
| "learning_rate": 0.00018847006651884703, |
| "loss": 0.6793, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.2175824175824176, |
| "grad_norm": 0.26335304975509644, |
| "learning_rate": 0.00018802660753880268, |
| "loss": 0.7131, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.22417582417582418, |
| "grad_norm": 0.25231942534446716, |
| "learning_rate": 0.00018758314855875832, |
| "loss": 0.7715, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.2437426745891571, |
| "learning_rate": 0.00018713968957871397, |
| "loss": 0.7094, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.23736263736263735, |
| "grad_norm": 0.28558826446533203, |
| "learning_rate": 0.00018669623059866964, |
| "loss": 0.6937, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.24395604395604395, |
| "grad_norm": 0.2915894687175751, |
| "learning_rate": 0.00018625277161862528, |
| "loss": 0.7238, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.25054945054945055, |
| "grad_norm": 0.25342074036598206, |
| "learning_rate": 0.00018580931263858095, |
| "loss": 0.7323, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 0.22744007408618927, |
| "learning_rate": 0.0001853658536585366, |
| "loss": 0.703, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.26373626373626374, |
| "grad_norm": 0.25383231043815613, |
| "learning_rate": 0.00018492239467849224, |
| "loss": 0.7093, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2703296703296703, |
| "grad_norm": 0.2194337695837021, |
| "learning_rate": 0.0001844789356984479, |
| "loss": 0.7367, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.27692307692307694, |
| "grad_norm": 0.32021859288215637, |
| "learning_rate": 0.00018403547671840356, |
| "loss": 0.6652, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.2835164835164835, |
| "grad_norm": 0.2328304797410965, |
| "learning_rate": 0.0001835920177383592, |
| "loss": 0.7016, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.29010989010989013, |
| "grad_norm": 0.24166613817214966, |
| "learning_rate": 0.00018314855875831487, |
| "loss": 0.6717, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.2967032967032967, |
| "grad_norm": 0.2733803391456604, |
| "learning_rate": 0.00018270509977827052, |
| "loss": 0.6979, |
| "step": 45 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 456, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 15, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.0757365016385536e+16, |
| "train_batch_size": 22, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
