Spaces:
Sleeping
Sleeping
| { | |
| "best_metric": 28.664, | |
| "best_model_checkpoint": "results/Legal-LED/IndiaABS/exp1\\checkpoint-1757", | |
| "epoch": 0.9997155049786629, | |
| "eval_steps": 500, | |
| "global_step": 1757, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 5.772658348083496, | |
| "learning_rate": 1.225e-05, | |
| "loss": 4.2551, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 2.3984649181365967, | |
| "learning_rate": 2.4750000000000002e-05, | |
| "loss": 3.4607, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 1.634371042251587, | |
| "learning_rate": 3.7250000000000004e-05, | |
| "loss": 2.7537, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 1.7180700302124023, | |
| "learning_rate": 4.975e-05, | |
| "loss": 2.5124, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 1.7759343385696411, | |
| "learning_rate": 4.842646114322415e-05, | |
| "loss": 2.3961, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 1.5487947463989258, | |
| "learning_rate": 4.6820809248554915e-05, | |
| "loss": 2.373, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.6271101236343384, | |
| "learning_rate": 4.521515735388568e-05, | |
| "loss": 2.3289, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 1.7767431735992432, | |
| "learning_rate": 4.360950545921644e-05, | |
| "loss": 2.3136, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 1.5476394891738892, | |
| "learning_rate": 4.2003853564547206e-05, | |
| "loss": 2.228, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 2.2447686195373535, | |
| "learning_rate": 4.039820166987797e-05, | |
| "loss": 2.2193, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 2.0830910205841064, | |
| "learning_rate": 3.879254977520873e-05, | |
| "loss": 2.244, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 1.8925021886825562, | |
| "learning_rate": 3.7186897880539504e-05, | |
| "loss": 2.2185, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 1.9989118576049805, | |
| "learning_rate": 3.558124598587027e-05, | |
| "loss": 2.2333, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.6363413333892822, | |
| "learning_rate": 3.397559409120103e-05, | |
| "loss": 2.1538, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 2.3027186393737793, | |
| "learning_rate": 3.2369942196531794e-05, | |
| "loss": 2.2577, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 1.6798630952835083, | |
| "learning_rate": 3.076429030186256e-05, | |
| "loss": 2.203, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 2.2237415313720703, | |
| "learning_rate": 2.915863840719332e-05, | |
| "loss": 2.1747, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 2.019179105758667, | |
| "learning_rate": 2.755298651252409e-05, | |
| "loss": 2.1642, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 1.8116823434829712, | |
| "learning_rate": 2.5947334617854852e-05, | |
| "loss": 2.0992, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 2.7756757736206055, | |
| "learning_rate": 2.4341682723185612e-05, | |
| "loss": 2.073, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.4382846355438232, | |
| "learning_rate": 2.2736030828516376e-05, | |
| "loss": 2.1295, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 1.680977702140808, | |
| "learning_rate": 2.1130378933847143e-05, | |
| "loss": 2.1131, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 2.0901172161102295, | |
| "learning_rate": 1.9524727039177907e-05, | |
| "loss": 2.145, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 1.953476071357727, | |
| "learning_rate": 1.791907514450867e-05, | |
| "loss": 2.1414, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 2.1726927757263184, | |
| "learning_rate": 1.6313423249839434e-05, | |
| "loss": 2.1293, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 1.8229079246520996, | |
| "learning_rate": 1.4707771355170199e-05, | |
| "loss": 2.1369, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 2.71445631980896, | |
| "learning_rate": 1.3102119460500964e-05, | |
| "loss": 2.0934, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 2.6795523166656494, | |
| "learning_rate": 1.1496467565831728e-05, | |
| "loss": 2.0734, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 2.1377625465393066, | |
| "learning_rate": 9.890815671162493e-06, | |
| "loss": 2.1422, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 1.7045388221740723, | |
| "learning_rate": 8.285163776493257e-06, | |
| "loss": 2.0615, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 2.001119375228882, | |
| "learning_rate": 6.679511881824021e-06, | |
| "loss": 2.0652, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 2.5513315200805664, | |
| "learning_rate": 5.0738599871547856e-06, | |
| "loss": 2.1465, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 1.8909486532211304, | |
| "learning_rate": 3.468208092485549e-06, | |
| "loss": 2.0798, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 1.9534186124801636, | |
| "learning_rate": 1.8625561978163134e-06, | |
| "loss": 2.0924, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.080364465713501, | |
| "learning_rate": 2.569043031470777e-07, | |
| "loss": 2.0598, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 815.03, | |
| "eval_loss": 2.0449941158294678, | |
| "eval_rouge1": 55.6012, | |
| "eval_rouge2": 28.664, | |
| "eval_rougeL": 26.4007, | |
| "eval_rougeLsum": 53.0454, | |
| "eval_runtime": 14551.3385, | |
| "eval_samples_per_second": 0.007, | |
| "eval_steps_per_second": 0.007, | |
| "step": 1757 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1757, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 3.806868794454835e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |