adapters-opt-gptq-QLORA-super_glue-multirc
/
trainer_state-opt-gptq-QLORA-super_glue-multirc-sequence_classification.json
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.984, | |
| "eval_steps": 1, | |
| "global_step": 124, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 26.392181396484375, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.2683, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "eval_exact_match": 0.14285714285714285, | |
| "eval_f1_a": 0.544, | |
| "eval_f1_m": 0.5331374974232117, | |
| "eval_loss": 0.9992128610610962, | |
| "eval_runtime": 12.4039, | |
| "eval_samples_per_second": 20.155, | |
| "eval_steps_per_second": 2.58, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 19.146682739257812, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0276, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "eval_exact_match": 0.12244897959183673, | |
| "eval_f1_a": 0.5344129554655871, | |
| "eval_f1_m": 0.5208925994640281, | |
| "eval_loss": 0.9813457131385803, | |
| "eval_runtime": 12.2968, | |
| "eval_samples_per_second": 20.331, | |
| "eval_steps_per_second": 2.602, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 25.024534225463867, | |
| "learning_rate": 4.959016393442623e-05, | |
| "loss": 1.1935, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4979253112033195, | |
| "eval_f1_m": 0.4637011514562535, | |
| "eval_loss": 0.9183418154716492, | |
| "eval_runtime": 12.5058, | |
| "eval_samples_per_second": 19.991, | |
| "eval_steps_per_second": 2.559, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 18.022754669189453, | |
| "learning_rate": 4.918032786885246e-05, | |
| "loss": 0.9304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.43243243243243246, | |
| "eval_f1_m": 0.42084400859911064, | |
| "eval_loss": 0.8643535375595093, | |
| "eval_runtime": 12.5036, | |
| "eval_samples_per_second": 19.994, | |
| "eval_steps_per_second": 2.559, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 17.011953353881836, | |
| "learning_rate": 4.8770491803278687e-05, | |
| "loss": 1.0187, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.44131455399061037, | |
| "eval_f1_m": 0.435791589363018, | |
| "eval_loss": 0.8290175795555115, | |
| "eval_runtime": 12.501, | |
| "eval_samples_per_second": 19.998, | |
| "eval_steps_per_second": 2.56, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 9.931246757507324, | |
| "learning_rate": 4.836065573770492e-05, | |
| "loss": 0.781, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.44761904761904764, | |
| "eval_f1_m": 0.44164457990988604, | |
| "eval_loss": 0.803396463394165, | |
| "eval_runtime": 12.603, | |
| "eval_samples_per_second": 19.837, | |
| "eval_steps_per_second": 2.539, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 34.31171417236328, | |
| "learning_rate": 4.795081967213115e-05, | |
| "loss": 1.2274, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.416243654822335, | |
| "eval_f1_m": 0.42698010606173864, | |
| "eval_loss": 0.7892948985099792, | |
| "eval_runtime": 12.5071, | |
| "eval_samples_per_second": 19.989, | |
| "eval_steps_per_second": 2.559, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 19.665807723999023, | |
| "learning_rate": 4.754098360655738e-05, | |
| "loss": 1.0631, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.3734939759036145, | |
| "eval_f1_m": 0.44151661996800046, | |
| "eval_loss": 0.779171884059906, | |
| "eval_runtime": 12.401, | |
| "eval_samples_per_second": 20.16, | |
| "eval_steps_per_second": 2.58, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 6.531087875366211, | |
| "learning_rate": 4.713114754098361e-05, | |
| "loss": 0.6823, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.24657534246575338, | |
| "eval_f1_m": 0.38393596199718655, | |
| "eval_loss": 0.7732793092727661, | |
| "eval_runtime": 12.3963, | |
| "eval_samples_per_second": 20.167, | |
| "eval_steps_per_second": 2.581, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 9.769821166992188, | |
| "learning_rate": 4.672131147540984e-05, | |
| "loss": 0.6971, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.24827586206896554, | |
| "eval_f1_m": 0.38636550524305635, | |
| "eval_loss": 0.7666972875595093, | |
| "eval_runtime": 12.3966, | |
| "eval_samples_per_second": 20.167, | |
| "eval_steps_per_second": 2.581, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "grad_norm": 18.875186920166016, | |
| "learning_rate": 4.631147540983607e-05, | |
| "loss": 0.8232, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.2028985507246377, | |
| "eval_f1_m": 0.37477658396025737, | |
| "eval_loss": 0.7616797089576721, | |
| "eval_runtime": 12.293, | |
| "eval_samples_per_second": 20.337, | |
| "eval_steps_per_second": 2.603, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 12.508312225341797, | |
| "learning_rate": 4.59016393442623e-05, | |
| "loss": 0.4358, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.2142857142857143, | |
| "eval_f1_m": 0.37786431255819003, | |
| "eval_loss": 0.7548164129257202, | |
| "eval_runtime": 12.2924, | |
| "eval_samples_per_second": 20.338, | |
| "eval_steps_per_second": 2.603, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.208, | |
| "grad_norm": 13.73599624633789, | |
| "learning_rate": 4.549180327868853e-05, | |
| "loss": 0.7875, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.208, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.21582733812949637, | |
| "eval_f1_m": 0.37958707958707955, | |
| "eval_loss": 0.7478398680686951, | |
| "eval_runtime": 12.293, | |
| "eval_samples_per_second": 20.337, | |
| "eval_steps_per_second": 2.603, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 17.087984085083008, | |
| "learning_rate": 4.508196721311476e-05, | |
| "loss": 0.9012, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.2377622377622378, | |
| "eval_f1_m": 0.38485918843061695, | |
| "eval_loss": 0.7398672103881836, | |
| "eval_runtime": 12.294, | |
| "eval_samples_per_second": 20.335, | |
| "eval_steps_per_second": 2.603, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 17.19772720336914, | |
| "learning_rate": 4.467213114754098e-05, | |
| "loss": 0.8344, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.24657534246575338, | |
| "eval_f1_m": 0.38393596199718655, | |
| "eval_loss": 0.7301445603370667, | |
| "eval_runtime": 12.3925, | |
| "eval_samples_per_second": 20.173, | |
| "eval_steps_per_second": 2.582, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 9.059144973754883, | |
| "learning_rate": 4.426229508196721e-05, | |
| "loss": 0.6957, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.3184713375796179, | |
| "eval_f1_m": 0.4192099850263115, | |
| "eval_loss": 0.7225546836853027, | |
| "eval_runtime": 12.2951, | |
| "eval_samples_per_second": 20.333, | |
| "eval_steps_per_second": 2.603, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.272, | |
| "grad_norm": 4.891639709472656, | |
| "learning_rate": 4.3852459016393444e-05, | |
| "loss": 0.6085, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.272, | |
| "eval_exact_match": 0.061224489795918366, | |
| "eval_f1_a": 0.3878787878787879, | |
| "eval_f1_m": 0.4543832318142042, | |
| "eval_loss": 0.7196054458618164, | |
| "eval_runtime": 12.2946, | |
| "eval_samples_per_second": 20.334, | |
| "eval_steps_per_second": 2.603, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 11.897939682006836, | |
| "learning_rate": 4.3442622950819674e-05, | |
| "loss": 0.7777, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.3976608187134503, | |
| "eval_f1_m": 0.4537870592792561, | |
| "eval_loss": 0.7144648432731628, | |
| "eval_runtime": 12.3977, | |
| "eval_samples_per_second": 20.165, | |
| "eval_steps_per_second": 2.581, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.304, | |
| "grad_norm": 11.019088745117188, | |
| "learning_rate": 4.3032786885245904e-05, | |
| "loss": 0.6732, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.304, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.39285714285714285, | |
| "eval_f1_m": 0.4570021548412905, | |
| "eval_loss": 0.7114218473434448, | |
| "eval_runtime": 12.3988, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 2.581, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 9.549395561218262, | |
| "learning_rate": 4.262295081967213e-05, | |
| "loss": 0.7477, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4046242774566474, | |
| "eval_f1_m": 0.4577005477515681, | |
| "eval_loss": 0.709179699420929, | |
| "eval_runtime": 12.4018, | |
| "eval_samples_per_second": 20.158, | |
| "eval_steps_per_second": 2.58, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 6.315933704376221, | |
| "learning_rate": 4.2213114754098365e-05, | |
| "loss": 0.6196, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4069767441860465, | |
| "eval_f1_m": 0.4574949710153791, | |
| "eval_loss": 0.7092265486717224, | |
| "eval_runtime": 12.2969, | |
| "eval_samples_per_second": 20.33, | |
| "eval_steps_per_second": 2.602, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 13.465363502502441, | |
| "learning_rate": 4.1803278688524595e-05, | |
| "loss": 0.8407, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4333333333333333, | |
| "eval_f1_m": 0.4608648720893619, | |
| "eval_loss": 0.7104062438011169, | |
| "eval_runtime": 12.3998, | |
| "eval_samples_per_second": 20.162, | |
| "eval_steps_per_second": 2.581, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.368, | |
| "grad_norm": 5.6240763664245605, | |
| "learning_rate": 4.1393442622950826e-05, | |
| "loss": 0.6945, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.368, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4175824175824176, | |
| "eval_f1_m": 0.4523820850351463, | |
| "eval_loss": 0.7099843621253967, | |
| "eval_runtime": 12.5009, | |
| "eval_samples_per_second": 19.999, | |
| "eval_steps_per_second": 2.56, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 11.571455001831055, | |
| "learning_rate": 4.098360655737705e-05, | |
| "loss": 0.7534, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.42774566473988435, | |
| "eval_f1_m": 0.4625007645415809, | |
| "eval_loss": 0.7112500071525574, | |
| "eval_runtime": 12.505, | |
| "eval_samples_per_second": 19.992, | |
| "eval_steps_per_second": 2.559, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 9.693904876708984, | |
| "learning_rate": 4.057377049180328e-05, | |
| "loss": 0.6428, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.32258064516129026, | |
| "eval_f1_m": 0.42786660784860053, | |
| "eval_loss": 0.7106679677963257, | |
| "eval_runtime": 12.5005, | |
| "eval_samples_per_second": 19.999, | |
| "eval_steps_per_second": 2.56, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 5.713263034820557, | |
| "learning_rate": 4.016393442622951e-05, | |
| "loss": 0.649, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.2638888888888889, | |
| "eval_f1_m": 0.4046327255510929, | |
| "eval_loss": 0.7118203043937683, | |
| "eval_runtime": 12.4034, | |
| "eval_samples_per_second": 20.156, | |
| "eval_steps_per_second": 2.58, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "grad_norm": 7.6466965675354, | |
| "learning_rate": 3.975409836065574e-05, | |
| "loss": 0.7344, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.18045112781954886, | |
| "eval_f1_m": 0.3727819799248371, | |
| "eval_loss": 0.7153554558753967, | |
| "eval_runtime": 12.4059, | |
| "eval_samples_per_second": 20.152, | |
| "eval_steps_per_second": 2.579, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 12.54140567779541, | |
| "learning_rate": 3.934426229508197e-05, | |
| "loss": 0.5762, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.13846153846153844, | |
| "eval_f1_m": 0.3607012601910561, | |
| "eval_loss": 0.7164726853370667, | |
| "eval_runtime": 12.4987, | |
| "eval_samples_per_second": 20.002, | |
| "eval_steps_per_second": 2.56, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.464, | |
| "grad_norm": 7.025119781494141, | |
| "learning_rate": 3.89344262295082e-05, | |
| "loss": 0.6606, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.464, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.11111111111111112, | |
| "eval_f1_m": 0.35377706194032715, | |
| "eval_loss": 0.719851553440094, | |
| "eval_runtime": 12.599, | |
| "eval_samples_per_second": 19.843, | |
| "eval_steps_per_second": 2.54, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 16.650728225708008, | |
| "learning_rate": 3.8524590163934424e-05, | |
| "loss": 0.6886, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.05454545454545454, | |
| "eval_f1_m": 0.3549857455469701, | |
| "eval_loss": 0.7235468626022339, | |
| "eval_runtime": 12.5049, | |
| "eval_samples_per_second": 19.992, | |
| "eval_steps_per_second": 2.559, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.496, | |
| "grad_norm": 9.604567527770996, | |
| "learning_rate": 3.8114754098360655e-05, | |
| "loss": 0.6693, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.496, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.03773584905660377, | |
| "eval_f1_m": 0.3570682452135034, | |
| "eval_loss": 0.730707049369812, | |
| "eval_runtime": 12.6051, | |
| "eval_samples_per_second": 19.833, | |
| "eval_steps_per_second": 2.539, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "grad_norm": 10.662591934204102, | |
| "learning_rate": 3.7704918032786885e-05, | |
| "loss": 0.8203, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.512, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019230769230769232, | |
| "eval_f1_m": 0.35394517780472173, | |
| "eval_loss": 0.7325780987739563, | |
| "eval_runtime": 12.5102, | |
| "eval_samples_per_second": 19.984, | |
| "eval_steps_per_second": 2.558, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.528, | |
| "grad_norm": 5.810702323913574, | |
| "learning_rate": 3.729508196721312e-05, | |
| "loss": 0.6831, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.528, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019230769230769232, | |
| "eval_f1_m": 0.35394517780472173, | |
| "eval_loss": 0.7296562790870667, | |
| "eval_runtime": 12.5052, | |
| "eval_samples_per_second": 19.992, | |
| "eval_steps_per_second": 2.559, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "grad_norm": 6.527573585510254, | |
| "learning_rate": 3.6885245901639346e-05, | |
| "loss": 0.6942, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.544, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019230769230769232, | |
| "eval_f1_m": 0.35394517780472173, | |
| "eval_loss": 0.7321445345878601, | |
| "eval_runtime": 12.6062, | |
| "eval_samples_per_second": 19.831, | |
| "eval_steps_per_second": 2.538, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 15.23520565032959, | |
| "learning_rate": 3.6475409836065576e-05, | |
| "loss": 0.7819, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019417475728155338, | |
| "eval_f1_m": 0.3550274288869728, | |
| "eval_loss": 0.7335781455039978, | |
| "eval_runtime": 12.6066, | |
| "eval_samples_per_second": 19.831, | |
| "eval_steps_per_second": 2.538, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "grad_norm": 12.970118522644043, | |
| "learning_rate": 3.6065573770491806e-05, | |
| "loss": 0.5959, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.576, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.3489535707722984, | |
| "eval_loss": 0.7367480397224426, | |
| "eval_runtime": 12.5014, | |
| "eval_samples_per_second": 19.998, | |
| "eval_steps_per_second": 2.56, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.592, | |
| "grad_norm": 9.984509468078613, | |
| "learning_rate": 3.5655737704918037e-05, | |
| "loss": 0.5692, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.592, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.3489535707722984, | |
| "eval_loss": 0.7453652620315552, | |
| "eval_runtime": 12.4005, | |
| "eval_samples_per_second": 20.16, | |
| "eval_steps_per_second": 2.581, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "grad_norm": 9.310087203979492, | |
| "learning_rate": 3.524590163934427e-05, | |
| "loss": 0.8538, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.608, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.7506445050239563, | |
| "eval_runtime": 12.5041, | |
| "eval_samples_per_second": 19.993, | |
| "eval_steps_per_second": 2.559, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.624, | |
| "grad_norm": 17.32353401184082, | |
| "learning_rate": 3.483606557377049e-05, | |
| "loss": 0.7333, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.624, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.7485976815223694, | |
| "eval_runtime": 12.605, | |
| "eval_samples_per_second": 19.833, | |
| "eval_steps_per_second": 2.539, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 9.058735847473145, | |
| "learning_rate": 3.442622950819672e-05, | |
| "loss": 0.4784, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.7543515563011169, | |
| "eval_runtime": 12.4985, | |
| "eval_samples_per_second": 20.002, | |
| "eval_steps_per_second": 2.56, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.656, | |
| "grad_norm": 15.80337142944336, | |
| "learning_rate": 3.401639344262295e-05, | |
| "loss": 0.8348, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.656, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.7519648671150208, | |
| "eval_runtime": 12.4002, | |
| "eval_samples_per_second": 20.161, | |
| "eval_steps_per_second": 2.581, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "grad_norm": 18.595117568969727, | |
| "learning_rate": 3.360655737704918e-05, | |
| "loss": 0.8212, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.672, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.7456523180007935, | |
| "eval_runtime": 12.5047, | |
| "eval_samples_per_second": 19.992, | |
| "eval_steps_per_second": 2.559, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.688, | |
| "grad_norm": 9.790151596069336, | |
| "learning_rate": 3.319672131147541e-05, | |
| "loss": 0.9515, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.688, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.3489535707722984, | |
| "eval_loss": 0.7356074452400208, | |
| "eval_runtime": 12.5029, | |
| "eval_samples_per_second": 19.995, | |
| "eval_steps_per_second": 2.559, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "grad_norm": 19.172956466674805, | |
| "learning_rate": 3.2786885245901635e-05, | |
| "loss": 0.8488, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.704, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019230769230769232, | |
| "eval_f1_m": 0.35394517780472173, | |
| "eval_loss": 0.7283183336257935, | |
| "eval_runtime": 12.6008, | |
| "eval_samples_per_second": 19.84, | |
| "eval_steps_per_second": 2.54, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 10.353903770446777, | |
| "learning_rate": 3.237704918032787e-05, | |
| "loss": 0.6007, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019230769230769232, | |
| "eval_f1_m": 0.35394517780472173, | |
| "eval_loss": 0.7258906364440918, | |
| "eval_runtime": 12.4066, | |
| "eval_samples_per_second": 20.15, | |
| "eval_steps_per_second": 2.579, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "grad_norm": 10.669143676757812, | |
| "learning_rate": 3.19672131147541e-05, | |
| "loss": 0.8167, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.736, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019230769230769232, | |
| "eval_f1_m": 0.35394517780472173, | |
| "eval_loss": 0.7255585789680481, | |
| "eval_runtime": 12.6073, | |
| "eval_samples_per_second": 19.83, | |
| "eval_steps_per_second": 2.538, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.752, | |
| "grad_norm": 12.651082992553711, | |
| "learning_rate": 3.155737704918033e-05, | |
| "loss": 0.7909, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.752, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019047619047619046, | |
| "eval_f1_m": 0.35264647650602043, | |
| "eval_loss": 0.7224531173706055, | |
| "eval_runtime": 12.5046, | |
| "eval_samples_per_second": 19.993, | |
| "eval_steps_per_second": 2.559, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "grad_norm": 16.77728843688965, | |
| "learning_rate": 3.114754098360656e-05, | |
| "loss": 0.7277, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.768, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.037383177570093455, | |
| "eval_f1_m": 0.3553675649413946, | |
| "eval_loss": 0.7222617268562317, | |
| "eval_runtime": 12.5048, | |
| "eval_samples_per_second": 19.992, | |
| "eval_steps_per_second": 2.559, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.784, | |
| "grad_norm": 9.990218162536621, | |
| "learning_rate": 3.073770491803279e-05, | |
| "loss": 0.6484, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.784, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.018867924528301886, | |
| "eval_f1_m": 0.35094579623391153, | |
| "eval_loss": 0.7233593463897705, | |
| "eval_runtime": 12.3979, | |
| "eval_samples_per_second": 20.165, | |
| "eval_steps_per_second": 2.581, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 19.805315017700195, | |
| "learning_rate": 3.0327868852459017e-05, | |
| "loss": 0.7366, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.05454545454545454, | |
| "eval_f1_m": 0.35851045213290117, | |
| "eval_loss": 0.7192890644073486, | |
| "eval_runtime": 12.394, | |
| "eval_samples_per_second": 20.171, | |
| "eval_steps_per_second": 2.582, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.816, | |
| "grad_norm": 6.260676860809326, | |
| "learning_rate": 2.9918032786885248e-05, | |
| "loss": 0.6544, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.816, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.07207207207207207, | |
| "eval_f1_m": 0.3631490108530924, | |
| "eval_loss": 0.7178593873977661, | |
| "eval_runtime": 12.399, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 2.581, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "grad_norm": 6.211192607879639, | |
| "learning_rate": 2.9508196721311478e-05, | |
| "loss": 0.5797, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.832, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.07142857142857144, | |
| "eval_f1_m": 0.36225194873154054, | |
| "eval_loss": 0.7176406383514404, | |
| "eval_runtime": 12.2942, | |
| "eval_samples_per_second": 20.335, | |
| "eval_steps_per_second": 2.603, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.848, | |
| "grad_norm": 19.603347778320312, | |
| "learning_rate": 2.9098360655737705e-05, | |
| "loss": 0.613, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.848, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.08928571428571429, | |
| "eval_f1_m": 0.36680547343812653, | |
| "eval_loss": 0.719406247138977, | |
| "eval_runtime": 12.2965, | |
| "eval_samples_per_second": 20.331, | |
| "eval_steps_per_second": 2.602, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "grad_norm": 7.0200042724609375, | |
| "learning_rate": 2.8688524590163935e-05, | |
| "loss": 0.7246, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.864, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.03773584905660377, | |
| "eval_f1_m": 0.35666626624009584, | |
| "eval_loss": 0.7230820059776306, | |
| "eval_runtime": 12.3942, | |
| "eval_samples_per_second": 20.171, | |
| "eval_steps_per_second": 2.582, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 7.6928791999816895, | |
| "learning_rate": 2.8278688524590162e-05, | |
| "loss": 0.723, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019230769230769232, | |
| "eval_f1_m": 0.35394517780472173, | |
| "eval_loss": 0.7283515334129333, | |
| "eval_runtime": 12.4051, | |
| "eval_samples_per_second": 20.153, | |
| "eval_steps_per_second": 2.58, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "grad_norm": 9.09825611114502, | |
| "learning_rate": 2.7868852459016392e-05, | |
| "loss": 0.526, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.896, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019230769230769232, | |
| "eval_f1_m": 0.35394517780472173, | |
| "eval_loss": 0.736648440361023, | |
| "eval_runtime": 12.5063, | |
| "eval_samples_per_second": 19.99, | |
| "eval_steps_per_second": 2.559, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.912, | |
| "grad_norm": 12.663421630859375, | |
| "learning_rate": 2.7459016393442626e-05, | |
| "loss": 0.7038, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.912, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.3489535707722984, | |
| "eval_loss": 0.7481816411018372, | |
| "eval_runtime": 12.4036, | |
| "eval_samples_per_second": 20.155, | |
| "eval_steps_per_second": 2.58, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "grad_norm": 15.922131538391113, | |
| "learning_rate": 2.7049180327868856e-05, | |
| "loss": 0.7805, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.928, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.7556718587875366, | |
| "eval_runtime": 12.4053, | |
| "eval_samples_per_second": 20.153, | |
| "eval_steps_per_second": 2.58, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.944, | |
| "grad_norm": 15.116573333740234, | |
| "learning_rate": 2.6639344262295087e-05, | |
| "loss": 0.7645, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.944, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.7615898251533508, | |
| "eval_runtime": 12.301, | |
| "eval_samples_per_second": 20.324, | |
| "eval_steps_per_second": 2.601, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 16.11196517944336, | |
| "learning_rate": 2.6229508196721314e-05, | |
| "loss": 0.802, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.762087881565094, | |
| "eval_runtime": 12.4045, | |
| "eval_samples_per_second": 20.154, | |
| "eval_steps_per_second": 2.58, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.976, | |
| "grad_norm": 11.784616470336914, | |
| "learning_rate": 2.5819672131147544e-05, | |
| "loss": 0.7266, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.976, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.7605761885643005, | |
| "eval_runtime": 12.5067, | |
| "eval_samples_per_second": 19.989, | |
| "eval_steps_per_second": 2.559, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "grad_norm": 5.855625152587891, | |
| "learning_rate": 2.540983606557377e-05, | |
| "loss": 0.6895, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.992, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.7616230249404907, | |
| "eval_runtime": 12.4021, | |
| "eval_samples_per_second": 20.158, | |
| "eval_steps_per_second": 2.58, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.008, | |
| "grad_norm": 12.561187744140625, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.8057, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.008, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.35077572820670067, | |
| "eval_loss": 0.7573671936988831, | |
| "eval_runtime": 12.5096, | |
| "eval_samples_per_second": 19.985, | |
| "eval_steps_per_second": 2.558, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.024, | |
| "grad_norm": 10.385027885437012, | |
| "learning_rate": 2.459016393442623e-05, | |
| "loss": 0.7454, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.024, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.0, | |
| "eval_f1_m": 0.3489535707722984, | |
| "eval_loss": 0.7491288781166077, | |
| "eval_runtime": 12.4029, | |
| "eval_samples_per_second": 20.157, | |
| "eval_steps_per_second": 2.58, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 15.67496395111084, | |
| "learning_rate": 2.418032786885246e-05, | |
| "loss": 0.877, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019417475728155338, | |
| "eval_f1_m": 0.3550274288869728, | |
| "eval_loss": 0.7429726719856262, | |
| "eval_runtime": 12.4019, | |
| "eval_samples_per_second": 20.158, | |
| "eval_steps_per_second": 2.58, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.056, | |
| "grad_norm": 14.67371654510498, | |
| "learning_rate": 2.377049180327869e-05, | |
| "loss": 0.7684, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.056, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.019230769230769232, | |
| "eval_f1_m": 0.35394517780472173, | |
| "eval_loss": 0.7341777086257935, | |
| "eval_runtime": 12.3064, | |
| "eval_samples_per_second": 20.315, | |
| "eval_steps_per_second": 2.6, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.072, | |
| "grad_norm": 11.17091178894043, | |
| "learning_rate": 2.336065573770492e-05, | |
| "loss": 0.6712, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.072, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.03669724770642201, | |
| "eval_f1_m": 0.34935849464660995, | |
| "eval_loss": 0.724734365940094, | |
| "eval_runtime": 12.4001, | |
| "eval_samples_per_second": 20.161, | |
| "eval_steps_per_second": 2.581, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.088, | |
| "grad_norm": 7.933443546295166, | |
| "learning_rate": 2.295081967213115e-05, | |
| "loss": 0.545, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.088, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.1, | |
| "eval_f1_m": 0.35936518130395684, | |
| "eval_loss": 0.7180312275886536, | |
| "eval_runtime": 12.6064, | |
| "eval_samples_per_second": 19.831, | |
| "eval_steps_per_second": 2.538, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.104, | |
| "grad_norm": 6.20879602432251, | |
| "learning_rate": 2.254098360655738e-05, | |
| "loss": 0.5563, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.104, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.15503875968992248, | |
| "eval_f1_m": 0.3728975672853224, | |
| "eval_loss": 0.7145351767539978, | |
| "eval_runtime": 12.3015, | |
| "eval_samples_per_second": 20.323, | |
| "eval_steps_per_second": 2.601, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 5.216189861297607, | |
| "learning_rate": 2.2131147540983607e-05, | |
| "loss": 0.5797, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.2222222222222222, | |
| "eval_f1_m": 0.3975035168912719, | |
| "eval_loss": 0.7122148275375366, | |
| "eval_runtime": 12.2962, | |
| "eval_samples_per_second": 20.331, | |
| "eval_steps_per_second": 2.602, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1360000000000001, | |
| "grad_norm": 4.51043701171875, | |
| "learning_rate": 2.1721311475409837e-05, | |
| "loss": 0.7785, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.1360000000000001, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.2571428571428571, | |
| "eval_f1_m": 0.4030671709243137, | |
| "eval_loss": 0.7087773680686951, | |
| "eval_runtime": 12.2926, | |
| "eval_samples_per_second": 20.337, | |
| "eval_steps_per_second": 2.603, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "grad_norm": 9.325611114501953, | |
| "learning_rate": 2.1311475409836064e-05, | |
| "loss": 0.757, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.152, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.3013698630136986, | |
| "eval_f1_m": 0.4158932903830863, | |
| "eval_loss": 0.7072968482971191, | |
| "eval_runtime": 12.3042, | |
| "eval_samples_per_second": 20.318, | |
| "eval_steps_per_second": 2.601, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.168, | |
| "grad_norm": 15.549028396606445, | |
| "learning_rate": 2.0901639344262298e-05, | |
| "loss": 0.85, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.168, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.3013698630136986, | |
| "eval_f1_m": 0.4126730412444698, | |
| "eval_loss": 0.7068906426429749, | |
| "eval_runtime": 12.3976, | |
| "eval_samples_per_second": 20.165, | |
| "eval_steps_per_second": 2.581, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.184, | |
| "grad_norm": 7.413804531097412, | |
| "learning_rate": 2.0491803278688525e-05, | |
| "loss": 0.6694, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.184, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.32258064516129026, | |
| "eval_f1_m": 0.41783029895274804, | |
| "eval_loss": 0.7051249742507935, | |
| "eval_runtime": 12.3988, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 2.581, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 13.059216499328613, | |
| "learning_rate": 2.0081967213114755e-05, | |
| "loss": 0.7654, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.3658536585365854, | |
| "eval_f1_m": 0.4367546285913633, | |
| "eval_loss": 0.7052109241485596, | |
| "eval_runtime": 12.3021, | |
| "eval_samples_per_second": 20.322, | |
| "eval_steps_per_second": 2.601, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.216, | |
| "grad_norm": 18.173431396484375, | |
| "learning_rate": 1.9672131147540985e-05, | |
| "loss": 0.7874, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.216, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.393063583815029, | |
| "eval_f1_m": 0.4441113308460247, | |
| "eval_loss": 0.7044414281845093, | |
| "eval_runtime": 12.3005, | |
| "eval_samples_per_second": 20.324, | |
| "eval_steps_per_second": 2.602, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.232, | |
| "grad_norm": 5.066444396972656, | |
| "learning_rate": 1.9262295081967212e-05, | |
| "loss": 0.585, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.232, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.4067796610169491, | |
| "eval_f1_m": 0.44523701921661113, | |
| "eval_loss": 0.7045234441757202, | |
| "eval_runtime": 12.4024, | |
| "eval_samples_per_second": 20.157, | |
| "eval_steps_per_second": 2.58, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.248, | |
| "grad_norm": 15.81064224243164, | |
| "learning_rate": 1.8852459016393442e-05, | |
| "loss": 0.7125, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.248, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.4347826086956522, | |
| "eval_f1_m": 0.45324236421175196, | |
| "eval_loss": 0.7049570083618164, | |
| "eval_runtime": 12.2997, | |
| "eval_samples_per_second": 20.326, | |
| "eval_steps_per_second": 2.602, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.264, | |
| "grad_norm": 15.786576271057129, | |
| "learning_rate": 1.8442622950819673e-05, | |
| "loss": 0.674, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.264, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.45263157894736844, | |
| "eval_f1_m": 0.45977191742497864, | |
| "eval_loss": 0.7056093811988831, | |
| "eval_runtime": 12.297, | |
| "eval_samples_per_second": 20.33, | |
| "eval_steps_per_second": 2.602, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 20.205602645874023, | |
| "learning_rate": 1.8032786885245903e-05, | |
| "loss": 0.7886, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.450261780104712, | |
| "eval_f1_m": 0.45734237417910883, | |
| "eval_loss": 0.706125020980835, | |
| "eval_runtime": 12.2957, | |
| "eval_samples_per_second": 20.332, | |
| "eval_steps_per_second": 2.603, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.296, | |
| "grad_norm": 7.352344036102295, | |
| "learning_rate": 1.7622950819672133e-05, | |
| "loss": 0.521, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.296, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.44329896907216493, | |
| "eval_f1_m": 0.44956970467174556, | |
| "eval_loss": 0.7077500224113464, | |
| "eval_runtime": 12.4027, | |
| "eval_samples_per_second": 20.157, | |
| "eval_steps_per_second": 2.58, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.312, | |
| "grad_norm": 9.654190063476562, | |
| "learning_rate": 1.721311475409836e-05, | |
| "loss": 0.7754, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.312, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.45226130653266333, | |
| "eval_f1_m": 0.45042921930677027, | |
| "eval_loss": 0.7080312371253967, | |
| "eval_runtime": 12.2984, | |
| "eval_samples_per_second": 20.328, | |
| "eval_steps_per_second": 2.602, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.328, | |
| "grad_norm": 19.156660079956055, | |
| "learning_rate": 1.680327868852459e-05, | |
| "loss": 0.7493, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.328, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4577114427860697, | |
| "eval_f1_m": 0.4507745089377742, | |
| "eval_loss": 0.7095780968666077, | |
| "eval_runtime": 12.2981, | |
| "eval_samples_per_second": 20.328, | |
| "eval_steps_per_second": 2.602, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "grad_norm": 4.014058589935303, | |
| "learning_rate": 1.6393442622950818e-05, | |
| "loss": 0.7076, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.3439999999999999, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.45999999999999996, | |
| "eval_f1_m": 0.45553641369967895, | |
| "eval_loss": 0.7096328139305115, | |
| "eval_runtime": 12.298, | |
| "eval_samples_per_second": 20.329, | |
| "eval_steps_per_second": 2.602, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 12.296324729919434, | |
| "learning_rate": 1.598360655737705e-05, | |
| "loss": 0.6649, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4577114427860697, | |
| "eval_f1_m": 0.4507745089377742, | |
| "eval_loss": 0.7094843983650208, | |
| "eval_runtime": 12.2932, | |
| "eval_samples_per_second": 20.337, | |
| "eval_steps_per_second": 2.603, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.376, | |
| "grad_norm": 8.357748985290527, | |
| "learning_rate": 1.557377049180328e-05, | |
| "loss": 0.6199, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.376, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.45544554455445546, | |
| "eval_f1_m": 0.44890376063845455, | |
| "eval_loss": 0.7101484537124634, | |
| "eval_runtime": 12.2925, | |
| "eval_samples_per_second": 20.338, | |
| "eval_steps_per_second": 2.603, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.392, | |
| "grad_norm": 5.569490909576416, | |
| "learning_rate": 1.5163934426229509e-05, | |
| "loss": 0.7666, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.392, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4577114427860697, | |
| "eval_f1_m": 0.4507745089377742, | |
| "eval_loss": 0.7110859155654907, | |
| "eval_runtime": 12.3978, | |
| "eval_samples_per_second": 20.165, | |
| "eval_steps_per_second": 2.581, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.408, | |
| "grad_norm": 20.458703994750977, | |
| "learning_rate": 1.4754098360655739e-05, | |
| "loss": 0.7505, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.408, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4577114427860697, | |
| "eval_f1_m": 0.4507745089377742, | |
| "eval_loss": 0.7112030982971191, | |
| "eval_runtime": 12.4088, | |
| "eval_samples_per_second": 20.147, | |
| "eval_steps_per_second": 2.579, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.424, | |
| "grad_norm": 17.410215377807617, | |
| "learning_rate": 1.4344262295081968e-05, | |
| "loss": 0.7426, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.424, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.45, | |
| "eval_f1_m": 0.4473113054745707, | |
| "eval_loss": 0.7114999890327454, | |
| "eval_runtime": 12.4068, | |
| "eval_samples_per_second": 20.15, | |
| "eval_steps_per_second": 2.579, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 12.000615119934082, | |
| "learning_rate": 1.3934426229508196e-05, | |
| "loss": 0.8439, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.45, | |
| "eval_f1_m": 0.4473113054745707, | |
| "eval_loss": 0.7099843621253967, | |
| "eval_runtime": 12.3004, | |
| "eval_samples_per_second": 20.325, | |
| "eval_steps_per_second": 2.602, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.456, | |
| "grad_norm": 9.254725456237793, | |
| "learning_rate": 1.3524590163934428e-05, | |
| "loss": 0.7011, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.456, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.44102564102564107, | |
| "eval_f1_m": 0.44650038170446327, | |
| "eval_loss": 0.7092187404632568, | |
| "eval_runtime": 12.6142, | |
| "eval_samples_per_second": 19.819, | |
| "eval_steps_per_second": 2.537, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.472, | |
| "grad_norm": 9.848048210144043, | |
| "learning_rate": 1.3114754098360657e-05, | |
| "loss": 0.689, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.472, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.45263157894736844, | |
| "eval_f1_m": 0.4581459923296658, | |
| "eval_loss": 0.7082812786102295, | |
| "eval_runtime": 12.4011, | |
| "eval_samples_per_second": 20.159, | |
| "eval_steps_per_second": 2.58, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.488, | |
| "grad_norm": 17.459680557250977, | |
| "learning_rate": 1.2704918032786885e-05, | |
| "loss": 0.8424, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.488, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.450261780104712, | |
| "eval_f1_m": 0.45620235773296997, | |
| "eval_loss": 0.7073437571525574, | |
| "eval_runtime": 12.4025, | |
| "eval_samples_per_second": 20.157, | |
| "eval_steps_per_second": 2.58, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.504, | |
| "grad_norm": 7.91733980178833, | |
| "learning_rate": 1.2295081967213116e-05, | |
| "loss": 0.6224, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.504, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4468085106382979, | |
| "eval_f1_m": 0.4566639709496852, | |
| "eval_loss": 0.7057031393051147, | |
| "eval_runtime": 12.4036, | |
| "eval_samples_per_second": 20.155, | |
| "eval_steps_per_second": 2.58, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 17.14729881286621, | |
| "learning_rate": 1.1885245901639344e-05, | |
| "loss": 0.5743, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.4491978609625668, | |
| "eval_f1_m": 0.4579678258249688, | |
| "eval_loss": 0.7053046822547913, | |
| "eval_runtime": 12.4028, | |
| "eval_samples_per_second": 20.157, | |
| "eval_steps_per_second": 2.58, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "grad_norm": 10.893065452575684, | |
| "learning_rate": 1.1475409836065575e-05, | |
| "loss": 0.7041, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.536, | |
| "eval_exact_match": 0.04081632653061224, | |
| "eval_f1_a": 0.44324324324324327, | |
| "eval_f1_m": 0.45810145070349156, | |
| "eval_loss": 0.7051210999488831, | |
| "eval_runtime": 12.3907, | |
| "eval_samples_per_second": 20.176, | |
| "eval_steps_per_second": 2.583, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.552, | |
| "grad_norm": 9.716265678405762, | |
| "learning_rate": 1.1065573770491803e-05, | |
| "loss": 0.6443, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.552, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.4262295081967213, | |
| "eval_f1_m": 0.4496709356403233, | |
| "eval_loss": 0.7061210870742798, | |
| "eval_runtime": 12.2983, | |
| "eval_samples_per_second": 20.328, | |
| "eval_steps_per_second": 2.602, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.568, | |
| "grad_norm": 17.185867309570312, | |
| "learning_rate": 1.0655737704918032e-05, | |
| "loss": 0.6588, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.568, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.430939226519337, | |
| "eval_f1_m": 0.4559391572146673, | |
| "eval_loss": 0.704464852809906, | |
| "eval_runtime": 12.4036, | |
| "eval_samples_per_second": 20.155, | |
| "eval_steps_per_second": 2.58, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.584, | |
| "grad_norm": 9.352198600769043, | |
| "learning_rate": 1.0245901639344262e-05, | |
| "loss": 0.6669, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.584, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.41860465116279066, | |
| "eval_f1_m": 0.45876048721186774, | |
| "eval_loss": 0.7052500247955322, | |
| "eval_runtime": 12.2869, | |
| "eval_samples_per_second": 20.347, | |
| "eval_steps_per_second": 2.604, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 10.983183860778809, | |
| "learning_rate": 9.836065573770493e-06, | |
| "loss": 0.667, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.3976608187134503, | |
| "eval_f1_m": 0.44378116214850916, | |
| "eval_loss": 0.7053242325782776, | |
| "eval_runtime": 12.292, | |
| "eval_samples_per_second": 20.338, | |
| "eval_steps_per_second": 2.603, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.616, | |
| "grad_norm": 8.352677345275879, | |
| "learning_rate": 9.426229508196721e-06, | |
| "loss": 0.6028, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.616, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.3780487804878049, | |
| "eval_f1_m": 0.440360093421318, | |
| "eval_loss": 0.7049765586853027, | |
| "eval_runtime": 12.3969, | |
| "eval_samples_per_second": 20.166, | |
| "eval_steps_per_second": 2.581, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.6320000000000001, | |
| "grad_norm": 18.418481826782227, | |
| "learning_rate": 9.016393442622952e-06, | |
| "loss": 0.7084, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.6320000000000001, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.3827160493827161, | |
| "eval_f1_m": 0.4446715982430268, | |
| "eval_loss": 0.7034218907356262, | |
| "eval_runtime": 12.3991, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 2.581, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.6480000000000001, | |
| "grad_norm": 10.633659362792969, | |
| "learning_rate": 8.60655737704918e-06, | |
| "loss": 0.6221, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.6480000000000001, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.33766233766233766, | |
| "eval_f1_m": 0.42304736080246286, | |
| "eval_loss": 0.7042617201805115, | |
| "eval_runtime": 12.2954, | |
| "eval_samples_per_second": 20.333, | |
| "eval_steps_per_second": 2.603, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.6640000000000001, | |
| "grad_norm": 12.377849578857422, | |
| "learning_rate": 8.196721311475409e-06, | |
| "loss": 0.5413, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.6640000000000001, | |
| "eval_exact_match": 0.02040816326530612, | |
| "eval_f1_a": 0.3289473684210526, | |
| "eval_f1_m": 0.4253797223184978, | |
| "eval_loss": 0.7033711075782776, | |
| "eval_runtime": 12.3003, | |
| "eval_samples_per_second": 20.325, | |
| "eval_steps_per_second": 2.602, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 12.551422119140625, | |
| "learning_rate": 7.78688524590164e-06, | |
| "loss": 0.682, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.2953020134228188, | |
| "eval_f1_m": 0.4078515022392573, | |
| "eval_loss": 0.7049804925918579, | |
| "eval_runtime": 12.495, | |
| "eval_samples_per_second": 20.008, | |
| "eval_steps_per_second": 2.561, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.696, | |
| "grad_norm": 8.237449645996094, | |
| "learning_rate": 7.3770491803278695e-06, | |
| "loss": 0.7448, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.696, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.3013698630136986, | |
| "eval_f1_m": 0.41549131140967865, | |
| "eval_loss": 0.7063398361206055, | |
| "eval_runtime": 12.4967, | |
| "eval_samples_per_second": 20.005, | |
| "eval_steps_per_second": 2.561, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.712, | |
| "grad_norm": 7.336461067199707, | |
| "learning_rate": 6.967213114754098e-06, | |
| "loss": 0.4493, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.712, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.2553191489361702, | |
| "eval_f1_m": 0.4051889720257066, | |
| "eval_loss": 0.7075039148330688, | |
| "eval_runtime": 12.403, | |
| "eval_samples_per_second": 20.156, | |
| "eval_steps_per_second": 2.58, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.728, | |
| "grad_norm": 8.348127365112305, | |
| "learning_rate": 6.557377049180328e-06, | |
| "loss": 0.8977, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.728, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.2608695652173913, | |
| "eval_f1_m": 0.4141215926930211, | |
| "eval_loss": 0.7066875100135803, | |
| "eval_runtime": 12.3958, | |
| "eval_samples_per_second": 20.168, | |
| "eval_steps_per_second": 2.582, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.744, | |
| "grad_norm": 6.762801170349121, | |
| "learning_rate": 6.147540983606558e-06, | |
| "loss": 0.6888, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.744, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.23529411764705882, | |
| "eval_f1_m": 0.4052051689806791, | |
| "eval_loss": 0.7079609632492065, | |
| "eval_runtime": 12.2957, | |
| "eval_samples_per_second": 20.332, | |
| "eval_steps_per_second": 2.603, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 7.54478645324707, | |
| "learning_rate": 5.737704918032787e-06, | |
| "loss": 0.7079, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.196969696969697, | |
| "eval_f1_m": 0.3930353659945496, | |
| "eval_loss": 0.7083203196525574, | |
| "eval_runtime": 12.4001, | |
| "eval_samples_per_second": 20.161, | |
| "eval_steps_per_second": 2.581, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.776, | |
| "grad_norm": 6.84658145904541, | |
| "learning_rate": 5.327868852459016e-06, | |
| "loss": 0.6766, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.776, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.2105263157894737, | |
| "eval_f1_m": 0.39676157176157173, | |
| "eval_loss": 0.7091640830039978, | |
| "eval_runtime": 12.4008, | |
| "eval_samples_per_second": 20.16, | |
| "eval_steps_per_second": 2.58, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.792, | |
| "grad_norm": 16.06954002380371, | |
| "learning_rate": 4.918032786885246e-06, | |
| "loss": 0.6298, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.792, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.15748031496062992, | |
| "eval_f1_m": 0.37861616841208684, | |
| "eval_loss": 0.7095195055007935, | |
| "eval_runtime": 12.4951, | |
| "eval_samples_per_second": 20.008, | |
| "eval_steps_per_second": 2.561, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.808, | |
| "grad_norm": 5.902178764343262, | |
| "learning_rate": 4.508196721311476e-06, | |
| "loss": 0.5864, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.808, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.15873015873015875, | |
| "eval_f1_m": 0.38075416646845217, | |
| "eval_loss": 0.7111679911613464, | |
| "eval_runtime": 12.4019, | |
| "eval_samples_per_second": 20.158, | |
| "eval_steps_per_second": 2.58, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.8239999999999998, | |
| "grad_norm": 17.344051361083984, | |
| "learning_rate": 4.098360655737704e-06, | |
| "loss": 0.7265, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.8239999999999998, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.16, | |
| "eval_f1_m": 0.38211471068613934, | |
| "eval_loss": 0.7119726538658142, | |
| "eval_runtime": 12.3958, | |
| "eval_samples_per_second": 20.168, | |
| "eval_steps_per_second": 2.582, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 13.185153007507324, | |
| "learning_rate": 3.6885245901639347e-06, | |
| "loss": 0.5856, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.15873015873015875, | |
| "eval_f1_m": 0.37997671262977384, | |
| "eval_loss": 0.7116367220878601, | |
| "eval_runtime": 12.3902, | |
| "eval_samples_per_second": 20.177, | |
| "eval_steps_per_second": 2.583, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.8559999999999999, | |
| "grad_norm": 6.701231956481934, | |
| "learning_rate": 3.278688524590164e-06, | |
| "loss": 0.718, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.8559999999999999, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.09836065573770492, | |
| "eval_f1_m": 0.361842380975034, | |
| "eval_loss": 0.7136015892028809, | |
| "eval_runtime": 12.294, | |
| "eval_samples_per_second": 20.335, | |
| "eval_steps_per_second": 2.603, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.8719999999999999, | |
| "grad_norm": 11.730875015258789, | |
| "learning_rate": 2.8688524590163937e-06, | |
| "loss": 0.7096, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.8719999999999999, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.08333333333333334, | |
| "eval_f1_m": 0.35354549079038877, | |
| "eval_loss": 0.7125195264816284, | |
| "eval_runtime": 12.3992, | |
| "eval_samples_per_second": 20.163, | |
| "eval_steps_per_second": 2.581, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.888, | |
| "grad_norm": 11.764548301696777, | |
| "learning_rate": 2.459016393442623e-06, | |
| "loss": 0.7648, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.888, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.10169491525423728, | |
| "eval_f1_m": 0.36885033900340025, | |
| "eval_loss": 0.7145312428474426, | |
| "eval_runtime": 12.2937, | |
| "eval_samples_per_second": 20.336, | |
| "eval_steps_per_second": 2.603, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.904, | |
| "grad_norm": 7.357093334197998, | |
| "learning_rate": 2.049180327868852e-06, | |
| "loss": 0.66, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.904, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.08403361344537816, | |
| "eval_f1_m": 0.3581008843763946, | |
| "eval_loss": 0.7142617106437683, | |
| "eval_runtime": 12.2932, | |
| "eval_samples_per_second": 20.336, | |
| "eval_steps_per_second": 2.603, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 12.222306251525879, | |
| "learning_rate": 1.639344262295082e-06, | |
| "loss": 0.7134, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.08620689655172413, | |
| "eval_f1_m": 0.3664693866224478, | |
| "eval_loss": 0.7143398523330688, | |
| "eval_runtime": 12.4037, | |
| "eval_samples_per_second": 20.155, | |
| "eval_steps_per_second": 2.58, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.936, | |
| "grad_norm": 11.94378662109375, | |
| "learning_rate": 1.2295081967213116e-06, | |
| "loss": 0.6269, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.936, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.06837606837606838, | |
| "eval_f1_m": 0.35452724712928796, | |
| "eval_loss": 0.7161992192268372, | |
| "eval_runtime": 12.2894, | |
| "eval_samples_per_second": 20.343, | |
| "eval_steps_per_second": 2.604, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.952, | |
| "grad_norm": 10.898783683776855, | |
| "learning_rate": 8.19672131147541e-07, | |
| "loss": 0.6692, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.952, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.06779661016949154, | |
| "eval_f1_m": 0.35377437355228475, | |
| "eval_loss": 0.7155507802963257, | |
| "eval_runtime": 12.2897, | |
| "eval_samples_per_second": 20.342, | |
| "eval_steps_per_second": 2.604, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.968, | |
| "grad_norm": 11.34163761138916, | |
| "learning_rate": 4.098360655737705e-07, | |
| "loss": 0.7837, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.968, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.06837606837606838, | |
| "eval_f1_m": 0.3542995836363184, | |
| "eval_loss": 0.7164883017539978, | |
| "eval_runtime": 12.3974, | |
| "eval_samples_per_second": 20.166, | |
| "eval_steps_per_second": 2.581, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.984, | |
| "grad_norm": 9.480073928833008, | |
| "learning_rate": 0.0, | |
| "loss": 0.5815, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.984, | |
| "eval_exact_match": 0.0, | |
| "eval_f1_a": 0.053097345132743355, | |
| "eval_f1_m": 0.35416089179594584, | |
| "eval_loss": 0.7167656421661377, | |
| "eval_runtime": 12.2934, | |
| "eval_samples_per_second": 20.336, | |
| "eval_steps_per_second": 2.603, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.984, | |
| "step": 124, | |
| "total_flos": 107566092058624.0, | |
| "train_loss": 0.7248697588520665, | |
| "train_runtime": 2001.1585, | |
| "train_samples_per_second": 0.999, | |
| "train_steps_per_second": 0.062 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 124, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "total_flos": 107566092058624.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |