|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.999734066128889, |
|
"eval_steps": 500, |
|
"global_step": 25380, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 4.9952133916247454e-05, |
|
"loss": 0.7972, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.980871895794772e-05, |
|
"loss": 0.7291, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.9570304302093216e-05, |
|
"loss": 0.7094, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.923780290675475e-05, |
|
"loss": 0.7107, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 4.881248801510328e-05, |
|
"loss": 0.6958, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 4.829598827979682e-05, |
|
"loss": 0.6906, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 4.7690281526402436e-05, |
|
"loss": 0.6803, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 4.699768717973511e-05, |
|
"loss": 0.6902, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 4.622085738211518e-05, |
|
"loss": 0.671, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 4.536276683755501e-05, |
|
"loss": 0.6747, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 4.442670142076442e-05, |
|
"loss": 0.6682, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 4.341624559459447e-05, |
|
"loss": 0.6545, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 4.233526868410146e-05, |
|
"loss": 0.6574, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 4.1187910059791954e-05, |
|
"loss": 0.6623, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 3.99785632867864e-05, |
|
"loss": 0.6684, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 3.871185930059859e-05, |
|
"loss": 0.6489, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 3.739264867395593e-05, |
|
"loss": 0.6594, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.06, |
|
"learning_rate": 3.6025983042565795e-05, |
|
"loss": 0.564, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 3.461709576095409e-05, |
|
"loss": 0.577, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 3.317138186245037e-05, |
|
"loss": 0.5692, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 3.169437740005849e-05, |
|
"loss": 0.5748, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 3.0191738247322414e-05, |
|
"loss": 0.5665, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 2.8669218440364937e-05, |
|
"loss": 0.5752, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 2.713264814403362e-05, |
|
"loss": 0.5591, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 2.5587911326528148e-05, |
|
"loss": 0.5618, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 2.4040923227999103e-05, |
|
"loss": 0.5586, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 2.2497607709397543e-05, |
|
"loss": 0.5674, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 1.65, |
|
"learning_rate": 2.096387456831309e-05, |
|
"loss": 0.5704, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 1.944559690866454e-05, |
|
"loss": 0.5632, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 1.77, |
|
"learning_rate": 1.794858865090123e-05, |
|
"loss": 0.5693, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 1.83, |
|
"learning_rate": 1.6478582268834674e-05, |
|
"loss": 0.5668, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 1.5041206838352956e-05, |
|
"loss": 0.5657, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 1.95, |
|
"learning_rate": 1.3641966482075208e-05, |
|
"loss": 0.5499, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 2.01, |
|
"learning_rate": 1.228621929248813e-05, |
|
"loss": 0.5471, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 2.07, |
|
"learning_rate": 1.0979156814273622e-05, |
|
"loss": 0.4683, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 9.72578416439587e-06, |
|
"loss": 0.468, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 8.530900866073433e-06, |
|
"loss": 0.4757, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 7.399082470028884e-06, |
|
"loss": 0.472, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 2.3, |
|
"learning_rate": 6.334663033393229e-06, |
|
"loss": 0.4652, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 5.341718523358624e-06, |
|
"loss": 0.4665, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 2.42, |
|
"learning_rate": 4.4240512091313994e-06, |
|
"loss": 0.4719, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 3.5851751019531088e-06, |
|
"loss": 0.4658, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 2.828302498944102e-06, |
|
"loss": 0.471, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 2.1563316822968333e-06, |
|
"loss": 0.4701, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 2.66, |
|
"learning_rate": 1.5718358209224153e-06, |
|
"loss": 0.4681, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 1.0770531170491289e-06, |
|
"loss": 0.4615, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 6.738782355044049e-07, |
|
"loss": 0.4687, |
|
"step": 23500 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 3.638550485000031e-07, |
|
"loss": 0.4629, |
|
"step": 24000 |
|
}, |
|
{ |
|
"epoch": 2.9, |
|
"learning_rate": 1.481707237026758e-07, |
|
"loss": 0.463, |
|
"step": 24500 |
|
}, |
|
{ |
|
"epoch": 2.95, |
|
"learning_rate": 2.7651178228807473e-08, |
|
"loss": 0.4716, |
|
"step": 25000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 25380, |
|
"total_flos": 1.6998673876237025e+18, |
|
"train_loss": 0.5736952250355148, |
|
"train_runtime": 159194.8564, |
|
"train_samples_per_second": 0.638, |
|
"train_steps_per_second": 0.159 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 25380, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 1.6998673876237025e+18, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|