|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 9.950248756218905, |
|
"eval_steps": 500, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.19900497512437812, |
|
"grad_norm": 0.258056640625, |
|
"learning_rate": 0.00019980267284282717, |
|
"loss": 0.7217, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.39800995024875624, |
|
"grad_norm": 0.217041015625, |
|
"learning_rate": 0.0001992114701314478, |
|
"loss": 0.665, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.5970149253731343, |
|
"grad_norm": 0.4091796875, |
|
"learning_rate": 0.0001982287250728689, |
|
"loss": 0.685, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.7960199004975125, |
|
"grad_norm": 0.393798828125, |
|
"learning_rate": 0.0001968583161128631, |
|
"loss": 0.7191, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.9950248756218906, |
|
"grad_norm": 0.33740234375, |
|
"learning_rate": 0.00019510565162951537, |
|
"loss": 0.7127, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.1940298507462686, |
|
"grad_norm": 1.5546875, |
|
"learning_rate": 0.00019297764858882514, |
|
"loss": 0.7251, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 1.3930348258706466, |
|
"grad_norm": 0.347412109375, |
|
"learning_rate": 0.00019048270524660196, |
|
"loss": 0.6989, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 1.5920398009950247, |
|
"grad_norm": 0.362060546875, |
|
"learning_rate": 0.00018763066800438636, |
|
"loss": 0.6677, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 1.7910447761194028, |
|
"grad_norm": 0.39794921875, |
|
"learning_rate": 0.00018443279255020152, |
|
"loss": 0.6782, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 1.9900497512437811, |
|
"grad_norm": 0.428955078125, |
|
"learning_rate": 0.00018090169943749476, |
|
"loss": 0.6859, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 2.189054726368159, |
|
"grad_norm": 0.41259765625, |
|
"learning_rate": 0.00017705132427757895, |
|
"loss": 0.6552, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 2.388059701492537, |
|
"grad_norm": 0.359130859375, |
|
"learning_rate": 0.00017289686274214118, |
|
"loss": 0.6583, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 2.587064676616915, |
|
"grad_norm": 0.425537109375, |
|
"learning_rate": 0.00016845471059286887, |
|
"loss": 0.647, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 2.7860696517412933, |
|
"grad_norm": 0.403564453125, |
|
"learning_rate": 0.000163742398974869, |
|
"loss": 0.6839, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 2.9850746268656714, |
|
"grad_norm": 0.406982421875, |
|
"learning_rate": 0.00015877852522924732, |
|
"loss": 0.6724, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 3.18407960199005, |
|
"grad_norm": 0.3798828125, |
|
"learning_rate": 0.00015358267949789966, |
|
"loss": 0.6476, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 3.383084577114428, |
|
"grad_norm": 0.41455078125, |
|
"learning_rate": 0.00014817536741017152, |
|
"loss": 0.6179, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 3.582089552238806, |
|
"grad_norm": 0.494140625, |
|
"learning_rate": 0.00014257792915650728, |
|
"loss": 0.6344, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 3.781094527363184, |
|
"grad_norm": 0.54443359375, |
|
"learning_rate": 0.00013681245526846783, |
|
"loss": 0.6503, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 3.9800995024875623, |
|
"grad_norm": 0.46484375, |
|
"learning_rate": 0.00013090169943749476, |
|
"loss": 0.6389, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 4.17910447761194, |
|
"grad_norm": 0.40673828125, |
|
"learning_rate": 0.0001248689887164855, |
|
"loss": 0.6063, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 4.378109452736318, |
|
"grad_norm": 0.494140625, |
|
"learning_rate": 0.00011873813145857249, |
|
"loss": 0.6267, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 4.577114427860696, |
|
"grad_norm": 0.443603515625, |
|
"learning_rate": 0.00011253332335643043, |
|
"loss": 0.6111, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 4.776119402985074, |
|
"grad_norm": 0.525390625, |
|
"learning_rate": 0.00010627905195293135, |
|
"loss": 0.6374, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 4.975124378109452, |
|
"grad_norm": 0.5419921875, |
|
"learning_rate": 0.0001, |
|
"loss": 0.6143, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 5.174129353233831, |
|
"grad_norm": 0.451416015625, |
|
"learning_rate": 9.372094804706867e-05, |
|
"loss": 0.5851, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 5.373134328358209, |
|
"grad_norm": 0.459716796875, |
|
"learning_rate": 8.746667664356956e-05, |
|
"loss": 0.6088, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 5.572139303482587, |
|
"grad_norm": 0.4765625, |
|
"learning_rate": 8.126186854142752e-05, |
|
"loss": 0.5803, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 5.7711442786069655, |
|
"grad_norm": 0.5380859375, |
|
"learning_rate": 7.513101128351454e-05, |
|
"loss": 0.6084, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 5.970149253731344, |
|
"grad_norm": 0.5205078125, |
|
"learning_rate": 6.909830056250527e-05, |
|
"loss": 0.599, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 6.169154228855722, |
|
"grad_norm": 0.52294921875, |
|
"learning_rate": 6.318754473153221e-05, |
|
"loss": 0.5874, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 6.3681592039801, |
|
"grad_norm": 0.5244140625, |
|
"learning_rate": 5.7422070843492734e-05, |
|
"loss": 0.5631, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 6.567164179104478, |
|
"grad_norm": 0.5087890625, |
|
"learning_rate": 5.182463258982846e-05, |
|
"loss": 0.5574, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 6.766169154228856, |
|
"grad_norm": 0.5107421875, |
|
"learning_rate": 4.6417320502100316e-05, |
|
"loss": 0.5902, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 6.965174129353234, |
|
"grad_norm": 0.53369140625, |
|
"learning_rate": 4.12214747707527e-05, |
|
"loss": 0.5869, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 7.164179104477612, |
|
"grad_norm": 0.54638671875, |
|
"learning_rate": 3.6257601025131026e-05, |
|
"loss": 0.5644, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 7.36318407960199, |
|
"grad_norm": 0.533203125, |
|
"learning_rate": 3.154528940713113e-05, |
|
"loss": 0.5528, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 7.562189054726368, |
|
"grad_norm": 0.5322265625, |
|
"learning_rate": 2.7103137257858868e-05, |
|
"loss": 0.5852, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 7.7611940298507465, |
|
"grad_norm": 0.5146484375, |
|
"learning_rate": 2.2948675722421086e-05, |
|
"loss": 0.5543, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 7.960199004975125, |
|
"grad_norm": 0.53955078125, |
|
"learning_rate": 1.9098300562505266e-05, |
|
"loss": 0.5786, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 8.159203980099502, |
|
"grad_norm": 0.48974609375, |
|
"learning_rate": 1.5567207449798515e-05, |
|
"loss": 0.5669, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 8.35820895522388, |
|
"grad_norm": 0.513671875, |
|
"learning_rate": 1.2369331995613665e-05, |
|
"loss": 0.5683, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 8.557213930348258, |
|
"grad_norm": 0.53076171875, |
|
"learning_rate": 9.517294753398064e-06, |
|
"loss": 0.5493, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 8.756218905472636, |
|
"grad_norm": 0.5400390625, |
|
"learning_rate": 7.022351411174866e-06, |
|
"loss": 0.5335, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 8.955223880597014, |
|
"grad_norm": 0.54833984375, |
|
"learning_rate": 4.8943483704846475e-06, |
|
"loss": 0.5649, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 9.154228855721392, |
|
"grad_norm": 0.5166015625, |
|
"learning_rate": 3.1416838871368924e-06, |
|
"loss": 0.5557, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 9.35323383084577, |
|
"grad_norm": 0.5068359375, |
|
"learning_rate": 1.771274927131139e-06, |
|
"loss": 0.5551, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 9.552238805970148, |
|
"grad_norm": 0.51708984375, |
|
"learning_rate": 7.885298685522235e-07, |
|
"loss": 0.5442, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 9.751243781094526, |
|
"grad_norm": 0.53564453125, |
|
"learning_rate": 1.973271571728441e-07, |
|
"loss": 0.5546, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 9.950248756218905, |
|
"grad_norm": 0.52880859375, |
|
"learning_rate": 0.0, |
|
"loss": 0.569, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 9.950248756218905, |
|
"step": 500, |
|
"total_flos": 2.4398694187008e+16, |
|
"train_loss": 0.6164851455688477, |
|
"train_runtime": 442.613, |
|
"train_samples_per_second": 4.541, |
|
"train_steps_per_second": 1.13 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 500, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 500, |
|
"total_flos": 2.4398694187008e+16, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|