| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9959721713658001, | |
| "eval_steps": 500, | |
| "global_step": 170, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02929329915781765, | |
| "grad_norm": 1.6078954935073853, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.9551, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0585865983156353, | |
| "grad_norm": 1.1429349184036255, | |
| "learning_rate": 4.9995716618706634e-05, | |
| "loss": 0.9029, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08787989747345294, | |
| "grad_norm": 0.7431623935699463, | |
| "learning_rate": 4.9845969445888354e-05, | |
| "loss": 0.7873, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1171731966312706, | |
| "grad_norm": 0.5352614521980286, | |
| "learning_rate": 4.948368129547296e-05, | |
| "loss": 0.7782, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14646649578908824, | |
| "grad_norm": 0.599611759185791, | |
| "learning_rate": 4.891229802725401e-05, | |
| "loss": 0.7671, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17575979494690588, | |
| "grad_norm": 0.5661498308181763, | |
| "learning_rate": 4.8137254283872696e-05, | |
| "loss": 0.7371, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.20505309410472355, | |
| "grad_norm": 0.4830688238143921, | |
| "learning_rate": 4.7165921799873716e-05, | |
| "loss": 0.7424, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2343463932625412, | |
| "grad_norm": 0.4806412160396576, | |
| "learning_rate": 4.6007539286346375e-05, | |
| "loss": 0.7218, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26363969242035884, | |
| "grad_norm": 0.43145492672920227, | |
| "learning_rate": 4.467312455804482e-05, | |
| "loss": 0.729, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2929329915781765, | |
| "grad_norm": 0.4414162337779999, | |
| "learning_rate": 4.317536973877955e-05, | |
| "loss": 0.7322, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3222262907359941, | |
| "grad_norm": 0.6285475492477417, | |
| "learning_rate": 4.1528520541821506e-05, | |
| "loss": 0.7152, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.35151958989381177, | |
| "grad_norm": 0.5875662565231323, | |
| "learning_rate": 3.974824077352845e-05, | |
| "loss": 0.744, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38081288905162947, | |
| "grad_norm": 0.5579010844230652, | |
| "learning_rate": 3.785146334895093e-05, | |
| "loss": 0.715, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4101061882094471, | |
| "grad_norm": 0.5400099754333496, | |
| "learning_rate": 3.58562292364649e-05, | |
| "loss": 0.7322, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.43939948736726475, | |
| "grad_norm": 0.43588295578956604, | |
| "learning_rate": 3.378151586328963e-05, | |
| "loss": 0.7098, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4686927865250824, | |
| "grad_norm": 0.42549237608909607, | |
| "learning_rate": 3.164705661399079e-05, | |
| "loss": 0.7227, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.49798608568290004, | |
| "grad_norm": 0.4135156273841858, | |
| "learning_rate": 2.947315313878701e-05, | |
| "loss": 0.6879, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5272793848407177, | |
| "grad_norm": 0.4909493029117584, | |
| "learning_rate": 2.7280482256866697e-05, | |
| "loss": 0.6863, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5565726839985353, | |
| "grad_norm": 0.44555437564849854, | |
| "learning_rate": 2.508989929133051e-05, | |
| "loss": 0.6977, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.585865983156353, | |
| "grad_norm": 0.4100770056247711, | |
| "learning_rate": 2.2922239706315745e-05, | |
| "loss": 0.7202, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6151592823141706, | |
| "grad_norm": 0.44192320108413696, | |
| "learning_rate": 2.079812093300668e-05, | |
| "loss": 0.6974, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6444525814719883, | |
| "grad_norm": 0.4109411835670471, | |
| "learning_rate": 1.8737746269439006e-05, | |
| "loss": 0.6709, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6737458806298059, | |
| "grad_norm": 0.3698427975177765, | |
| "learning_rate": 1.6760712719281375e-05, | |
| "loss": 0.6868, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7030391797876235, | |
| "grad_norm": 0.3567708730697632, | |
| "learning_rate": 1.4885824597312362e-05, | |
| "loss": 0.6767, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7323324789454412, | |
| "grad_norm": 0.37050729990005493, | |
| "learning_rate": 1.313091467446158e-05, | |
| "loss": 0.6788, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7616257781032589, | |
| "grad_norm": 0.35710033774375916, | |
| "learning_rate": 1.1512674563572253e-05, | |
| "loss": 0.6797, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.7909190772610766, | |
| "grad_norm": 0.328642874956131, | |
| "learning_rate": 1.0046495959150554e-05, | |
| "loss": 0.6554, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8202123764188942, | |
| "grad_norm": 0.3246113359928131, | |
| "learning_rate": 8.746324241130455e-06, | |
| "loss": 0.6895, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8495056755767119, | |
| "grad_norm": 0.3387470543384552, | |
| "learning_rate": 7.624525835084185e-06, | |
| "loss": 0.6864, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8787989747345295, | |
| "grad_norm": 0.34192147850990295, | |
| "learning_rate": 6.691770590465606e-06, | |
| "loss": 0.6718, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9080922738923471, | |
| "grad_norm": 0.3072430491447449, | |
| "learning_rate": 5.95693029563144e-06, | |
| "loss": 0.673, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9373855730501648, | |
| "grad_norm": 0.32493317127227783, | |
| "learning_rate": 5.426994294902611e-06, | |
| "loss": 0.6767, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9666788722079824, | |
| "grad_norm": 0.32937249541282654, | |
| "learning_rate": 5.10700301026355e-06, | |
| "loss": 0.6815, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9959721713658001, | |
| "grad_norm": 0.3123301863670349, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6732, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9959721713658001, | |
| "step": 170, | |
| "total_flos": 77096571633664.0, | |
| "train_loss": 0.7200509982950547, | |
| "train_runtime": 16045.7979, | |
| "train_samples_per_second": 0.34, | |
| "train_steps_per_second": 0.011 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 170, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 77096571633664.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |