| { | |
| "best_metric": 0.5931050181388855, | |
| "best_model_checkpoint": "/content/drive/MyDrive/Projects/nitic-nlp-team/webnavix/checkpoints/webnavix/nitic-nlp-team/webnavix-llama-booking/checkpoint-200", | |
| "epoch": 4.022988505747127, | |
| "eval_steps": 50, | |
| "global_step": 1050, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0038314176245210726, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 4.9961685823754786e-05, | |
| "loss": 0.4159, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.038314176245210725, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 4.96168582375479e-05, | |
| "loss": 0.4866, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07662835249042145, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 4.9233716475095786e-05, | |
| "loss": 0.4732, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11494252873563218, | |
| "grad_norm": 0.59375, | |
| "learning_rate": 4.885057471264368e-05, | |
| "loss": 0.4579, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1532567049808429, | |
| "grad_norm": 0.50390625, | |
| "learning_rate": 4.846743295019157e-05, | |
| "loss": 0.4311, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19157088122605365, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 4.8084291187739464e-05, | |
| "loss": 0.4089, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19157088122605365, | |
| "eval_loss": 0.6184551119804382, | |
| "eval_runtime": 26.7423, | |
| "eval_samples_per_second": 12.564, | |
| "eval_steps_per_second": 0.785, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22988505747126436, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 4.770114942528736e-05, | |
| "loss": 0.4348, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2681992337164751, | |
| "grad_norm": 0.546875, | |
| "learning_rate": 4.7318007662835254e-05, | |
| "loss": 0.4154, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3065134099616858, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 4.693486590038315e-05, | |
| "loss": 0.4223, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 0.6015625, | |
| "learning_rate": 4.655172413793104e-05, | |
| "loss": 0.4139, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3831417624521073, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 4.616858237547893e-05, | |
| "loss": 0.3993, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3831417624521073, | |
| "eval_loss": 0.6077439188957214, | |
| "eval_runtime": 26.2148, | |
| "eval_samples_per_second": 12.817, | |
| "eval_steps_per_second": 0.801, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.421455938697318, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 4.578544061302682e-05, | |
| "loss": 0.3817, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.45977011494252873, | |
| "grad_norm": 0.6171875, | |
| "learning_rate": 4.5402298850574716e-05, | |
| "loss": 0.3852, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.49808429118773945, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 4.501915708812261e-05, | |
| "loss": 0.4068, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5363984674329502, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 4.46360153256705e-05, | |
| "loss": 0.3825, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5747126436781609, | |
| "grad_norm": 0.671875, | |
| "learning_rate": 4.4252873563218394e-05, | |
| "loss": 0.3659, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5747126436781609, | |
| "eval_loss": 0.6019139289855957, | |
| "eval_runtime": 26.1659, | |
| "eval_samples_per_second": 12.841, | |
| "eval_steps_per_second": 0.803, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6130268199233716, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 4.386973180076628e-05, | |
| "loss": 0.3789, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6513409961685823, | |
| "grad_norm": 0.60546875, | |
| "learning_rate": 4.348659003831418e-05, | |
| "loss": 0.3811, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6896551724137931, | |
| "grad_norm": 0.65234375, | |
| "learning_rate": 4.3103448275862066e-05, | |
| "loss": 0.3764, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7279693486590039, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 4.272030651340996e-05, | |
| "loss": 0.3763, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7662835249042146, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 4.2337164750957856e-05, | |
| "loss": 0.3677, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7662835249042146, | |
| "eval_loss": 0.5931050181388855, | |
| "eval_runtime": 26.7154, | |
| "eval_samples_per_second": 12.577, | |
| "eval_steps_per_second": 0.786, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8045977011494253, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 4.195402298850575e-05, | |
| "loss": 0.3599, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.842911877394636, | |
| "grad_norm": 0.70703125, | |
| "learning_rate": 4.1570881226053646e-05, | |
| "loss": 0.3551, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8812260536398467, | |
| "grad_norm": 0.72265625, | |
| "learning_rate": 4.1187739463601534e-05, | |
| "loss": 0.3605, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9195402298850575, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 4.080459770114943e-05, | |
| "loss": 0.3449, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9578544061302682, | |
| "grad_norm": 0.83203125, | |
| "learning_rate": 4.0421455938697324e-05, | |
| "loss": 0.3406, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9578544061302682, | |
| "eval_loss": 0.5955321192741394, | |
| "eval_runtime": 26.2482, | |
| "eval_samples_per_second": 12.801, | |
| "eval_steps_per_second": 0.8, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9961685823754789, | |
| "grad_norm": 0.87890625, | |
| "learning_rate": 4.003831417624521e-05, | |
| "loss": 0.3312, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0344827586206897, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 3.965517241379311e-05, | |
| "loss": 0.2937, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.0727969348659003, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 3.9272030651340996e-05, | |
| "loss": 0.2811, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.7109375, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.2833, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.1494252873563218, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 3.850574712643678e-05, | |
| "loss": 0.2892, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1494252873563218, | |
| "eval_loss": 0.6218650341033936, | |
| "eval_runtime": 26.3134, | |
| "eval_samples_per_second": 12.769, | |
| "eval_steps_per_second": 0.798, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1877394636015326, | |
| "grad_norm": 0.98046875, | |
| "learning_rate": 3.8122605363984674e-05, | |
| "loss": 0.258, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.2260536398467432, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 3.773946360153257e-05, | |
| "loss": 0.2554, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.264367816091954, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 3.735632183908046e-05, | |
| "loss": 0.2605, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.3026819923371646, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 3.697318007662835e-05, | |
| "loss": 0.2914, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.3409961685823755, | |
| "grad_norm": 0.73046875, | |
| "learning_rate": 3.659003831417625e-05, | |
| "loss": 0.2774, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.3409961685823755, | |
| "eval_loss": 0.6224318146705627, | |
| "eval_runtime": 26.3353, | |
| "eval_samples_per_second": 12.759, | |
| "eval_steps_per_second": 0.797, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 1.15625, | |
| "learning_rate": 3.620689655172414e-05, | |
| "loss": 0.2596, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.417624521072797, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 3.582375478927204e-05, | |
| "loss": 0.2655, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.4559386973180077, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 3.5440613026819926e-05, | |
| "loss": 0.2635, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.4942528735632183, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 3.505747126436782e-05, | |
| "loss": 0.257, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.5325670498084292, | |
| "grad_norm": 0.75390625, | |
| "learning_rate": 3.467432950191571e-05, | |
| "loss": 0.2429, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5325670498084292, | |
| "eval_loss": 0.6327727437019348, | |
| "eval_runtime": 26.3275, | |
| "eval_samples_per_second": 12.762, | |
| "eval_steps_per_second": 0.798, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5708812260536398, | |
| "grad_norm": 0.88671875, | |
| "learning_rate": 3.4291187739463604e-05, | |
| "loss": 0.2453, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.6091954022988506, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 3.390804597701149e-05, | |
| "loss": 0.2338, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.6475095785440614, | |
| "grad_norm": 0.90234375, | |
| "learning_rate": 3.352490421455939e-05, | |
| "loss": 0.2514, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.685823754789272, | |
| "grad_norm": 0.828125, | |
| "learning_rate": 3.314176245210728e-05, | |
| "loss": 0.25, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 0.8125, | |
| "learning_rate": 3.275862068965517e-05, | |
| "loss": 0.2412, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "eval_loss": 0.6357457637786865, | |
| "eval_runtime": 26.2278, | |
| "eval_samples_per_second": 12.811, | |
| "eval_steps_per_second": 0.801, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.7624521072796935, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 3.2375478927203066e-05, | |
| "loss": 0.2436, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.8007662835249043, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 3.1992337164750954e-05, | |
| "loss": 0.2357, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.839080459770115, | |
| "grad_norm": 0.80078125, | |
| "learning_rate": 3.160919540229885e-05, | |
| "loss": 0.248, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.8773946360153255, | |
| "grad_norm": 0.8515625, | |
| "learning_rate": 3.1226053639846744e-05, | |
| "loss": 0.2385, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.9157088122605364, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 3.084291187739464e-05, | |
| "loss": 0.2415, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9157088122605364, | |
| "eval_loss": 0.6407597661018372, | |
| "eval_runtime": 26.2269, | |
| "eval_samples_per_second": 12.811, | |
| "eval_steps_per_second": 0.801, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9540229885057472, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 3.045977011494253e-05, | |
| "loss": 0.2019, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.9923371647509578, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 3.0076628352490422e-05, | |
| "loss": 0.2286, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.0306513409961684, | |
| "grad_norm": 0.86328125, | |
| "learning_rate": 2.9693486590038317e-05, | |
| "loss": 0.1773, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.0689655172413794, | |
| "grad_norm": 0.75, | |
| "learning_rate": 2.9310344827586206e-05, | |
| "loss": 0.183, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.10727969348659, | |
| "grad_norm": 0.75, | |
| "learning_rate": 2.89272030651341e-05, | |
| "loss": 0.1924, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.10727969348659, | |
| "eval_loss": 0.6760431528091431, | |
| "eval_runtime": 26.5714, | |
| "eval_samples_per_second": 12.645, | |
| "eval_steps_per_second": 0.79, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.1455938697318007, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 2.8544061302681996e-05, | |
| "loss": 0.176, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.1839080459770113, | |
| "grad_norm": 0.79296875, | |
| "learning_rate": 2.8160919540229884e-05, | |
| "loss": 0.1618, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.7734375, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1785, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.260536398467433, | |
| "grad_norm": 0.82421875, | |
| "learning_rate": 2.739463601532567e-05, | |
| "loss": 0.1742, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 2.7011494252873566e-05, | |
| "loss": 0.1825, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "eval_loss": 0.6811310648918152, | |
| "eval_runtime": 26.2351, | |
| "eval_samples_per_second": 12.807, | |
| "eval_steps_per_second": 0.8, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.3371647509578546, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 2.662835249042146e-05, | |
| "loss": 0.1892, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.375478927203065, | |
| "grad_norm": 0.7421875, | |
| "learning_rate": 2.624521072796935e-05, | |
| "loss": 0.1561, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.413793103448276, | |
| "grad_norm": 0.75, | |
| "learning_rate": 2.5862068965517244e-05, | |
| "loss": 0.163, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.4521072796934864, | |
| "grad_norm": 0.84375, | |
| "learning_rate": 2.5478927203065132e-05, | |
| "loss": 0.1754, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.4904214559386975, | |
| "grad_norm": 0.8515625, | |
| "learning_rate": 2.5095785440613027e-05, | |
| "loss": 0.1828, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.4904214559386975, | |
| "eval_loss": 0.6785231232643127, | |
| "eval_runtime": 26.4019, | |
| "eval_samples_per_second": 12.726, | |
| "eval_steps_per_second": 0.795, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.528735632183908, | |
| "grad_norm": 0.8203125, | |
| "learning_rate": 2.4712643678160922e-05, | |
| "loss": 0.1706, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.5670498084291187, | |
| "grad_norm": 0.75, | |
| "learning_rate": 2.4329501915708814e-05, | |
| "loss": 0.1565, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 2.6053639846743293, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 2.3946360153256706e-05, | |
| "loss": 0.1636, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 2.6436781609195403, | |
| "grad_norm": 0.76953125, | |
| "learning_rate": 2.3563218390804597e-05, | |
| "loss": 0.183, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.681992337164751, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 2.3180076628352492e-05, | |
| "loss": 0.1767, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.681992337164751, | |
| "eval_loss": 0.6805046796798706, | |
| "eval_runtime": 26.3352, | |
| "eval_samples_per_second": 12.759, | |
| "eval_steps_per_second": 0.797, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.7203065134099615, | |
| "grad_norm": 0.86328125, | |
| "learning_rate": 2.2796934865900384e-05, | |
| "loss": 0.1746, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.7586206896551726, | |
| "grad_norm": 0.81640625, | |
| "learning_rate": 2.2413793103448276e-05, | |
| "loss": 0.1557, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.796934865900383, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 2.203065134099617e-05, | |
| "loss": 0.1656, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.835249042145594, | |
| "grad_norm": 0.7265625, | |
| "learning_rate": 2.1647509578544062e-05, | |
| "loss": 0.1656, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.873563218390805, | |
| "grad_norm": 0.73828125, | |
| "learning_rate": 2.1264367816091954e-05, | |
| "loss": 0.1689, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.873563218390805, | |
| "eval_loss": 0.6861817240715027, | |
| "eval_runtime": 26.3615, | |
| "eval_samples_per_second": 12.746, | |
| "eval_steps_per_second": 0.797, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.9118773946360155, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 2.088122605363985e-05, | |
| "loss": 0.1648, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.950191570881226, | |
| "grad_norm": 0.7890625, | |
| "learning_rate": 2.049808429118774e-05, | |
| "loss": 0.1571, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.9885057471264367, | |
| "grad_norm": 0.8671875, | |
| "learning_rate": 2.0114942528735632e-05, | |
| "loss": 0.1746, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.0268199233716473, | |
| "grad_norm": 0.71875, | |
| "learning_rate": 1.9731800766283527e-05, | |
| "loss": 0.1266, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.0651340996168583, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.934865900383142e-05, | |
| "loss": 0.1388, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.0651340996168583, | |
| "eval_loss": 0.718950629234314, | |
| "eval_runtime": 26.6936, | |
| "eval_samples_per_second": 12.587, | |
| "eval_steps_per_second": 0.787, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.103448275862069, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.896551724137931e-05, | |
| "loss": 0.1437, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.1417624521072796, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.8582375478927206e-05, | |
| "loss": 0.1379, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.1800766283524906, | |
| "grad_norm": 0.61328125, | |
| "learning_rate": 1.8199233716475097e-05, | |
| "loss": 0.1257, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.218390804597701, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 1.781609195402299e-05, | |
| "loss": 0.1332, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.256704980842912, | |
| "grad_norm": 0.71484375, | |
| "learning_rate": 1.743295019157088e-05, | |
| "loss": 0.1494, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.256704980842912, | |
| "eval_loss": 0.7269139289855957, | |
| "eval_runtime": 26.3692, | |
| "eval_samples_per_second": 12.742, | |
| "eval_steps_per_second": 0.796, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.2950191570881224, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.7049808429118776e-05, | |
| "loss": 0.1495, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.1434, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 3.371647509578544, | |
| "grad_norm": 0.67578125, | |
| "learning_rate": 1.628352490421456e-05, | |
| "loss": 0.1368, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 3.4099616858237547, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.5900383141762454e-05, | |
| "loss": 0.1276, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "grad_norm": 0.69921875, | |
| "learning_rate": 1.5517241379310346e-05, | |
| "loss": 0.1412, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.4482758620689653, | |
| "eval_loss": 0.7323886752128601, | |
| "eval_runtime": 26.3242, | |
| "eval_samples_per_second": 12.764, | |
| "eval_steps_per_second": 0.798, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.4865900383141764, | |
| "grad_norm": 0.6953125, | |
| "learning_rate": 1.5134099616858237e-05, | |
| "loss": 0.1351, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 3.524904214559387, | |
| "grad_norm": 0.74609375, | |
| "learning_rate": 1.475095785440613e-05, | |
| "loss": 0.1307, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 3.5632183908045976, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.4367816091954022e-05, | |
| "loss": 0.1246, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 3.6015325670498086, | |
| "grad_norm": 0.75, | |
| "learning_rate": 1.3984674329501916e-05, | |
| "loss": 0.1236, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 3.6398467432950192, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 1.360153256704981e-05, | |
| "loss": 0.1404, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.6398467432950192, | |
| "eval_loss": 0.7346541285514832, | |
| "eval_runtime": 26.3295, | |
| "eval_samples_per_second": 12.761, | |
| "eval_steps_per_second": 0.798, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 3.67816091954023, | |
| "grad_norm": 0.703125, | |
| "learning_rate": 1.3218390804597702e-05, | |
| "loss": 0.1501, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.716475095785441, | |
| "grad_norm": 0.66796875, | |
| "learning_rate": 1.2835249042145594e-05, | |
| "loss": 0.1381, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 3.7547892720306515, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 1.2452107279693487e-05, | |
| "loss": 0.1171, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 3.793103448275862, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 1.206896551724138e-05, | |
| "loss": 0.1223, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 3.8314176245210727, | |
| "grad_norm": 0.68359375, | |
| "learning_rate": 1.1685823754789272e-05, | |
| "loss": 0.1216, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.8314176245210727, | |
| "eval_loss": 0.7364165186882019, | |
| "eval_runtime": 26.387, | |
| "eval_samples_per_second": 12.734, | |
| "eval_steps_per_second": 0.796, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.8697318007662833, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 1.1302681992337164e-05, | |
| "loss": 0.1409, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 3.9080459770114944, | |
| "grad_norm": 0.65625, | |
| "learning_rate": 1.091954022988506e-05, | |
| "loss": 0.1395, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 3.946360153256705, | |
| "grad_norm": 0.6640625, | |
| "learning_rate": 1.053639846743295e-05, | |
| "loss": 0.1246, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 3.9846743295019156, | |
| "grad_norm": 0.8046875, | |
| "learning_rate": 1.0153256704980842e-05, | |
| "loss": 0.1328, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 4.022988505747127, | |
| "grad_norm": 0.625, | |
| "learning_rate": 9.770114942528738e-06, | |
| "loss": 0.1154, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.022988505747127, | |
| "eval_loss": 0.7410662174224854, | |
| "eval_runtime": 26.5729, | |
| "eval_samples_per_second": 12.644, | |
| "eval_steps_per_second": 0.79, | |
| "step": 1050 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1305, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.286105767649485e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |