| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012583798359612, | |
| "eval_steps": 42, | |
| "global_step": 84, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014980712332871428, | |
| "eval_loss": 1.160882592201233, | |
| "eval_runtime": 311.16, | |
| "eval_samples_per_second": 36.133, | |
| "eval_steps_per_second": 4.519, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00044942136998614283, | |
| "grad_norm": 0.12129199504852295, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.1193, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008988427399722857, | |
| "grad_norm": 0.11971050500869751, | |
| "learning_rate": 3e-05, | |
| "loss": 1.103, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013482641099584285, | |
| "grad_norm": 0.10862895101308823, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.0659, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017976854799445713, | |
| "grad_norm": 0.11977853626012802, | |
| "learning_rate": 4.9997944716957985e-05, | |
| "loss": 1.0914, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0022471068499307144, | |
| "grad_norm": 0.12554779648780823, | |
| "learning_rate": 4.99871554050172e-05, | |
| "loss": 1.1725, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002696528219916857, | |
| "grad_norm": 0.13287784159183502, | |
| "learning_rate": 4.996712222958461e-05, | |
| "loss": 1.1145, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003145949589903, | |
| "grad_norm": 0.1167389452457428, | |
| "learning_rate": 4.993785260182552e-05, | |
| "loss": 1.0956, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0035953709598891426, | |
| "grad_norm": 0.11548212915658951, | |
| "learning_rate": 4.989935734988098e-05, | |
| "loss": 1.12, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004044792329875285, | |
| "grad_norm": 0.12251826375722885, | |
| "learning_rate": 4.9851650714862006e-05, | |
| "loss": 1.0895, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004494213699861429, | |
| "grad_norm": 0.12304849177598953, | |
| "learning_rate": 4.979475034558115e-05, | |
| "loss": 1.1302, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004943635069847571, | |
| "grad_norm": 0.12594439089298248, | |
| "learning_rate": 4.9728677292023405e-05, | |
| "loss": 1.0825, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005393056439833714, | |
| "grad_norm": 0.11802031844854355, | |
| "learning_rate": 4.965345599755887e-05, | |
| "loss": 1.0949, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005842477809819857, | |
| "grad_norm": 0.12052260339260101, | |
| "learning_rate": 4.95691142899001e-05, | |
| "loss": 1.2106, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006291899179806, | |
| "grad_norm": 0.14151117205619812, | |
| "learning_rate": 4.9475683370807326e-05, | |
| "loss": 1.0855, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006291899179806, | |
| "eval_loss": 1.1297273635864258, | |
| "eval_runtime": 313.2801, | |
| "eval_samples_per_second": 35.888, | |
| "eval_steps_per_second": 4.488, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006741320549792143, | |
| "grad_norm": 0.13759616017341614, | |
| "learning_rate": 4.937319780454559e-05, | |
| "loss": 1.1133, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007190741919778285, | |
| "grad_norm": 0.14887671172618866, | |
| "learning_rate": 4.926169550509787e-05, | |
| "loss": 1.1339, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.007640163289764428, | |
| "grad_norm": 0.13235358893871307, | |
| "learning_rate": 4.914121772213898e-05, | |
| "loss": 1.0057, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.00808958465975057, | |
| "grad_norm": 0.14951473474502563, | |
| "learning_rate": 4.9011809025775486e-05, | |
| "loss": 1.0919, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.008539006029736713, | |
| "grad_norm": 0.1409119963645935, | |
| "learning_rate": 4.887351729005726e-05, | |
| "loss": 1.143, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.008988427399722857, | |
| "grad_norm": 0.13198496401309967, | |
| "learning_rate": 4.8726393675266716e-05, | |
| "loss": 1.0853, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.009437848769709, | |
| "grad_norm": 0.15319645404815674, | |
| "learning_rate": 4.8570492608992325e-05, | |
| "loss": 1.0534, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.009887270139695143, | |
| "grad_norm": 0.1532219797372818, | |
| "learning_rate": 4.8405871765993433e-05, | |
| "loss": 1.1016, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.010336691509681285, | |
| "grad_norm": 0.14198264479637146, | |
| "learning_rate": 4.82325920468638e-05, | |
| "loss": 1.029, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.010786112879667428, | |
| "grad_norm": 0.12415461987257004, | |
| "learning_rate": 4.805071755550177e-05, | |
| "loss": 1.1565, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.01123553424965357, | |
| "grad_norm": 0.1350441873073578, | |
| "learning_rate": 4.7860315575395316e-05, | |
| "loss": 1.1276, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.011684955619639713, | |
| "grad_norm": 0.12075574696063995, | |
| "learning_rate": 4.766145654473095e-05, | |
| "loss": 1.0753, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.012134376989625857, | |
| "grad_norm": 0.11550460755825043, | |
| "learning_rate": 4.745421403033548e-05, | |
| "loss": 1.0078, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.012583798359612, | |
| "grad_norm": 0.12455905228853226, | |
| "learning_rate": 4.72386647004603e-05, | |
| "loss": 1.0373, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.012583798359612, | |
| "eval_loss": 1.1157194375991821, | |
| "eval_runtime": 312.8234, | |
| "eval_samples_per_second": 35.94, | |
| "eval_steps_per_second": 4.495, | |
| "step": 84 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 42, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.765900651220173e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |