|
{ |
|
"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": 0.0, |
|
"learning_rate": 1.25e-05, |
|
"loss": 1347.2, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.09010632546404758, |
|
"grad_norm": 3153.3505859375, |
|
"learning_rate": 2.5e-05, |
|
"loss": 477.367, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.13515948819607138, |
|
"grad_norm": 1858.1285400390625, |
|
"learning_rate": 3.7500000000000003e-05, |
|
"loss": 442.957, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.18021265092809516, |
|
"grad_norm": 2545.223388671875, |
|
"learning_rate": 5e-05, |
|
"loss": 433.9167, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.22526581366011894, |
|
"grad_norm": 2296.039794921875, |
|
"learning_rate": 4.990486745229364e-05, |
|
"loss": 418.3493, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.27031897639214275, |
|
"grad_norm": 2642.889404296875, |
|
"learning_rate": 4.962019382530521e-05, |
|
"loss": 407.9998, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.3153721391241665, |
|
"grad_norm": 0.0, |
|
"learning_rate": 4.914814565722671e-05, |
|
"loss": 410.2617, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.3604253018561903, |
|
"grad_norm": 2563.190673828125, |
|
"learning_rate": 4.849231551964771e-05, |
|
"loss": 397.9934, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.40547846458821407, |
|
"grad_norm": 3283.779052734375, |
|
"learning_rate": 4.765769467591625e-05, |
|
"loss": 417.8361, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.4505316273202379, |
|
"grad_norm": 2174.240234375, |
|
"learning_rate": 4.665063509461097e-05, |
|
"loss": 375.8966, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.4955847900522617, |
|
"grad_norm": 2514.682373046875, |
|
"learning_rate": 4.54788011072248e-05, |
|
"loss": 388.2395, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.5406379527842855, |
|
"grad_norm": 3136.03759765625, |
|
"learning_rate": 4.415111107797445e-05, |
|
"loss": 394.8071, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.5856911155163093, |
|
"grad_norm": 1837.290283203125, |
|
"learning_rate": 4.267766952966369e-05, |
|
"loss": 366.3096, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.630744278248333, |
|
"grad_norm": 2366.833740234375, |
|
"learning_rate": 4.1069690242163484e-05, |
|
"loss": 367.1677, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.6757974409803568, |
|
"grad_norm": 2263.440673828125, |
|
"learning_rate": 3.933941090877615e-05, |
|
"loss": 372.6355, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 0.7208506037123806, |
|
"grad_norm": 2522.50244140625, |
|
"learning_rate": 3.7500000000000003e-05, |
|
"loss": 367.763, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 0.7659037664444044, |
|
"grad_norm": 2936.105712890625, |
|
"learning_rate": 3.556545654351749e-05, |
|
"loss": 354.5393, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 0.8109569291764281, |
|
"grad_norm": 0.0, |
|
"learning_rate": 3.355050358314172e-05, |
|
"loss": 362.7008, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 0.856010091908452, |
|
"grad_norm": 2301.9541015625, |
|
"learning_rate": 3.147047612756302e-05, |
|
"loss": 339.9951, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 0.9010632546404758, |
|
"grad_norm": 2941.145751953125, |
|
"learning_rate": 2.9341204441673266e-05, |
|
"loss": 357.0448, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 0.9461164173724995, |
|
"grad_norm": 2575.2666015625, |
|
"learning_rate": 2.717889356869146e-05, |
|
"loss": 356.5437, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 0.9911695801045234, |
|
"grad_norm": 3181.543212890625, |
|
"learning_rate": 2.5e-05, |
|
"loss": 350.985, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 382.581298828125, |
|
"eval_runtime": 227.6629, |
|
"eval_samples_per_second": 43.332, |
|
"eval_steps_per_second": 5.42, |
|
"step": 11098 |
|
}, |
|
{ |
|
"epoch": 1.0362227428365471, |
|
"grad_norm": 2919.064208984375, |
|
"learning_rate": 2.2821106431308544e-05, |
|
"loss": 328.9697, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.081275905568571, |
|
"grad_norm": 1792.9368896484375, |
|
"learning_rate": 2.0658795558326743e-05, |
|
"loss": 316.0124, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 1.1263290683005946, |
|
"grad_norm": 3145.044921875, |
|
"learning_rate": 1.852952387243698e-05, |
|
"loss": 318.4672, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 1.1713822310326185, |
|
"grad_norm": 2122.60693359375, |
|
"learning_rate": 1.6449496416858284e-05, |
|
"loss": 310.955, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 1.2164353937646424, |
|
"grad_norm": 0.0, |
|
"learning_rate": 1.443454345648252e-05, |
|
"loss": 308.6115, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 1.261488556496666, |
|
"grad_norm": 2367.4453125, |
|
"learning_rate": 1.2500000000000006e-05, |
|
"loss": 308.7791, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 1.30654171922869, |
|
"grad_norm": 3921.755126953125, |
|
"learning_rate": 1.0660589091223855e-05, |
|
"loss": 314.4502, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 1.3515948819607138, |
|
"grad_norm": 3169.499267578125, |
|
"learning_rate": 8.930309757836517e-06, |
|
"loss": 299.5019, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 1.3966480446927374, |
|
"grad_norm": 1866.3717041015625, |
|
"learning_rate": 7.3223304703363135e-06, |
|
"loss": 303.1934, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 1.4417012074247613, |
|
"grad_norm": 2293.599365234375, |
|
"learning_rate": 5.848888922025553e-06, |
|
"loss": 299.5156, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 1.4867543701567851, |
|
"grad_norm": 2268.71142578125, |
|
"learning_rate": 4.521198892775203e-06, |
|
"loss": 307.7869, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 1.5318075328888088, |
|
"grad_norm": 3546.200439453125, |
|
"learning_rate": 3.3493649053890326e-06, |
|
"loss": 290.4306, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 1.5768606956208324, |
|
"grad_norm": 2096.766845703125, |
|
"learning_rate": 2.3423053240837515e-06, |
|
"loss": 299.7911, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 1.6219138583528565, |
|
"grad_norm": 0.0, |
|
"learning_rate": 1.5076844803522922e-06, |
|
"loss": 302.4306, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 1.6669670210848802, |
|
"grad_norm": 1852.839111328125, |
|
"learning_rate": 8.51854342773295e-07, |
|
"loss": 305.6073, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 1.7120201838169038, |
|
"grad_norm": 2610.0205078125, |
|
"learning_rate": 3.7980617469479953e-07, |
|
"loss": 308.6735, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 1.7570733465489279, |
|
"grad_norm": 1428.6187744140625, |
|
"learning_rate": 9.513254770636137e-08, |
|
"loss": 296.7373, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 1.8021265092809515, |
|
"grad_norm": 0.0, |
|
"learning_rate": 0.0, |
|
"loss": 290.4464, |
|
"step": 20000 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 20000, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 10000, |
|
"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 |
|
} |
|
|