| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8021265092809515, | |
| "eval_steps": 500, | |
| "global_step": 20000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04505316273202379, | |
| "grad_norm": 5023.73388671875, | |
| "learning_rate": 1.25e-05, | |
| "loss": 2425.6955, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09010632546404758, | |
| "grad_norm": 4085.17724609375, | |
| "learning_rate": 2.5e-05, | |
| "loss": 633.1036, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13515948819607138, | |
| "grad_norm": 3114.9833984375, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 586.7181, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.18021265092809516, | |
| "grad_norm": 3313.659423828125, | |
| "learning_rate": 5e-05, | |
| "loss": 565.9839, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.22526581366011894, | |
| "grad_norm": 2783.360107421875, | |
| "learning_rate": 4.990486745229364e-05, | |
| "loss": 558.0812, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.27031897639214275, | |
| "grad_norm": 3958.57763671875, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 542.2432, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3153721391241665, | |
| "grad_norm": 2197.1630859375, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 521.7359, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.3604253018561903, | |
| "grad_norm": 2326.522705078125, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 522.5125, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.40547846458821407, | |
| "grad_norm": 2209.858642578125, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 514.8256, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4505316273202379, | |
| "grad_norm": 2931.34130859375, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 500.6537, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.4955847900522617, | |
| "grad_norm": 2907.71484375, | |
| "learning_rate": 4.54788011072248e-05, | |
| "loss": 497.3337, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.5406379527842855, | |
| "grad_norm": 1822.9918212890625, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 484.2432, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.5856911155163093, | |
| "grad_norm": 2211.70458984375, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 489.1086, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.630744278248333, | |
| "grad_norm": 1908.6292724609375, | |
| "learning_rate": 4.1069690242163484e-05, | |
| "loss": 487.3377, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.6757974409803568, | |
| "grad_norm": 3507.5302734375, | |
| "learning_rate": 3.933941090877615e-05, | |
| "loss": 479.4596, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.7208506037123806, | |
| "grad_norm": 2594.98291015625, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 487.1899, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.7659037664444044, | |
| "grad_norm": 2933.35595703125, | |
| "learning_rate": 3.556545654351749e-05, | |
| "loss": 482.0614, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.8109569291764281, | |
| "grad_norm": 2508.786376953125, | |
| "learning_rate": 3.355050358314172e-05, | |
| "loss": 469.1376, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.856010091908452, | |
| "grad_norm": 2515.1328125, | |
| "learning_rate": 3.147047612756302e-05, | |
| "loss": 462.4763, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.9010632546404758, | |
| "grad_norm": 2034.9927978515625, | |
| "learning_rate": 2.9341204441673266e-05, | |
| "loss": 459.6087, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.9461164173724995, | |
| "grad_norm": 1929.3106689453125, | |
| "learning_rate": 2.717889356869146e-05, | |
| "loss": 453.5379, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.9911695801045234, | |
| "grad_norm": 2851.670654296875, | |
| "learning_rate": 2.5e-05, | |
| "loss": 453.0242, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 428.85467529296875, | |
| "eval_runtime": 57.9798, | |
| "eval_samples_per_second": 170.145, | |
| "eval_steps_per_second": 21.283, | |
| "step": 11098 | |
| }, | |
| { | |
| "epoch": 1.0362227428365471, | |
| "grad_norm": 2632.15185546875, | |
| "learning_rate": 2.2821106431308544e-05, | |
| "loss": 437.7418, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.081275905568571, | |
| "grad_norm": 2240.501220703125, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 438.0496, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.1263290683005946, | |
| "grad_norm": 1960.9959716796875, | |
| "learning_rate": 1.852952387243698e-05, | |
| "loss": 427.4685, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.1713822310326185, | |
| "grad_norm": 2526.84228515625, | |
| "learning_rate": 1.6449496416858284e-05, | |
| "loss": 429.6636, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.2164353937646424, | |
| "grad_norm": 2094.966552734375, | |
| "learning_rate": 1.443454345648252e-05, | |
| "loss": 429.0512, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.261488556496666, | |
| "grad_norm": 1433.662109375, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 436.467, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.30654171922869, | |
| "grad_norm": 1956.2445068359375, | |
| "learning_rate": 1.0660589091223855e-05, | |
| "loss": 422.1393, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.3515948819607138, | |
| "grad_norm": 2243.373779296875, | |
| "learning_rate": 8.930309757836517e-06, | |
| "loss": 429.4757, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.3966480446927374, | |
| "grad_norm": 2793.48095703125, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 422.5827, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.4417012074247613, | |
| "grad_norm": 2228.3212890625, | |
| "learning_rate": 5.848888922025553e-06, | |
| "loss": 430.6597, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.4867543701567851, | |
| "grad_norm": 3403.7626953125, | |
| "learning_rate": 4.521198892775203e-06, | |
| "loss": 426.2394, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.5318075328888088, | |
| "grad_norm": 1795.3551025390625, | |
| "learning_rate": 3.3493649053890326e-06, | |
| "loss": 422.1375, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.5768606956208324, | |
| "grad_norm": 3233.425537109375, | |
| "learning_rate": 2.3423053240837515e-06, | |
| "loss": 426.7428, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.6219138583528565, | |
| "grad_norm": 2393.4365234375, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 422.9055, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.6669670210848802, | |
| "grad_norm": 2255.08837890625, | |
| "learning_rate": 8.51854342773295e-07, | |
| "loss": 418.1114, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.7120201838169038, | |
| "grad_norm": 1896.0711669921875, | |
| "learning_rate": 3.7980617469479953e-07, | |
| "loss": 419.0474, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.7570733465489279, | |
| "grad_norm": 2811.251953125, | |
| "learning_rate": 9.513254770636137e-08, | |
| "loss": 424.493, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.8021265092809515, | |
| "grad_norm": 2713.771484375, | |
| "learning_rate": 0.0, | |
| "loss": 423.2755, | |
| "step": 20000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 20000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |