| { | |
| "best_metric": 0.23586615753847973, | |
| "best_model_checkpoint": "/content/drive/MyDrive/model_outputs/trial_5/checkpoint-292", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 438, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0684931506849315, | |
| "grad_norm": 5.608231067657471, | |
| "learning_rate": 3.6003360497121445e-06, | |
| "loss": 2.2214, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 5.646218776702881, | |
| "learning_rate": 7.200672099424289e-06, | |
| "loss": 2.1624, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2054794520547945, | |
| "grad_norm": 5.6624908447265625, | |
| "learning_rate": 1.041544648904501e-05, | |
| "loss": 2.1074, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 5.1634697914123535, | |
| "learning_rate": 1.0160165937842927e-05, | |
| "loss": 2.0965, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "grad_norm": 4.445455551147461, | |
| "learning_rate": 9.904885386640843e-06, | |
| "loss": 2.0527, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 4.640649795532227, | |
| "learning_rate": 9.64960483543876e-06, | |
| "loss": 2.0678, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4794520547945205, | |
| "grad_norm": 5.322652816772461, | |
| "learning_rate": 9.394324284236676e-06, | |
| "loss": 2.0892, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 5.406436443328857, | |
| "learning_rate": 9.139043733034592e-06, | |
| "loss": 2.0179, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6164383561643836, | |
| "grad_norm": 4.761965751647949, | |
| "learning_rate": 8.883763181832509e-06, | |
| "loss": 2.0074, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 4.901184558868408, | |
| "learning_rate": 8.628482630630425e-06, | |
| "loss": 2.0241, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7534246575342466, | |
| "grad_norm": 5.2895941734313965, | |
| "learning_rate": 8.373202079428341e-06, | |
| "loss": 2.0019, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 4.653793811798096, | |
| "learning_rate": 8.117921528226258e-06, | |
| "loss": 2.0277, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8904109589041096, | |
| "grad_norm": 5.342679977416992, | |
| "learning_rate": 7.862640977024174e-06, | |
| "loss": 1.9835, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 5.529128074645996, | |
| "learning_rate": 7.607360425822091e-06, | |
| "loss": 2.0019, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_classification_report": { | |
| "accuracy": 0.2285, | |
| "ar": { | |
| "f1-score": 0.0547945205479452, | |
| "precision": 0.46153846153846156, | |
| "recall": 0.02912621359223301, | |
| "support": 206.0 | |
| }, | |
| "cl": { | |
| "f1-score": 0.2222222222222222, | |
| "precision": 0.18932038834951456, | |
| "recall": 0.2689655172413793, | |
| "support": 290.0 | |
| }, | |
| "co": { | |
| "f1-score": 0.2832980972515856, | |
| "precision": 0.20458015267175572, | |
| "recall": 0.46048109965635736, | |
| "support": 291.0 | |
| }, | |
| "es": { | |
| "f1-score": 0.2547993019197208, | |
| "precision": 0.24829931972789115, | |
| "recall": 0.2616487455197133, | |
| "support": 279.0 | |
| }, | |
| "macro avg": { | |
| "f1-score": 0.1991778548194697, | |
| "precision": 0.27210428357115557, | |
| "recall": 0.2048681078220834, | |
| "support": 2000.0 | |
| }, | |
| "mx": { | |
| "f1-score": 0.23859649122807017, | |
| "precision": 0.24372759856630824, | |
| "recall": 0.23367697594501718, | |
| "support": 291.0 | |
| }, | |
| "pe": { | |
| "f1-score": 0.174573055028463, | |
| "precision": 0.19491525423728814, | |
| "recall": 0.15807560137457044, | |
| "support": 291.0 | |
| }, | |
| "pr": { | |
| "f1-score": 0.4567901234567901, | |
| "precision": 0.6065573770491803, | |
| "recall": 0.36633663366336633, | |
| "support": 101.0 | |
| }, | |
| "uy": { | |
| "f1-score": 0.10752688172043011, | |
| "precision": 0.3, | |
| "recall": 0.06550218340611354, | |
| "support": 229.0 | |
| }, | |
| "ve": { | |
| "f1-score": 0.0, | |
| "precision": 0.0, | |
| "recall": 0.0, | |
| "support": 22.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.21012633177845003, | |
| "precision": 0.2681977677888293, | |
| "recall": 0.2285, | |
| "support": 2000.0 | |
| } | |
| }, | |
| "eval_f1": 0.1991778548194697, | |
| "eval_loss": 1.9731428623199463, | |
| "eval_runtime": 3.5688, | |
| "eval_samples_per_second": 560.405, | |
| "eval_steps_per_second": 17.653, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.0273972602739727, | |
| "grad_norm": 4.819364547729492, | |
| "learning_rate": 7.352079874620008e-06, | |
| "loss": 1.9655, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.095890410958904, | |
| "grad_norm": 5.056692123413086, | |
| "learning_rate": 7.096799323417924e-06, | |
| "loss": 1.9654, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.1643835616438356, | |
| "grad_norm": 5.491762638092041, | |
| "learning_rate": 6.8415187722158405e-06, | |
| "loss": 1.9755, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.2328767123287672, | |
| "grad_norm": 5.931197643280029, | |
| "learning_rate": 6.586238221013757e-06, | |
| "loss": 1.9487, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3013698630136985, | |
| "grad_norm": 6.085172176361084, | |
| "learning_rate": 6.330957669811673e-06, | |
| "loss": 1.9436, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.36986301369863, | |
| "grad_norm": 6.041102409362793, | |
| "learning_rate": 6.07567711860959e-06, | |
| "loss": 1.9561, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.4383561643835616, | |
| "grad_norm": 5.231081008911133, | |
| "learning_rate": 5.820396567407506e-06, | |
| "loss": 1.959, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.5068493150684932, | |
| "grad_norm": 5.686812400817871, | |
| "learning_rate": 5.565116016205422e-06, | |
| "loss": 1.8635, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.5753424657534247, | |
| "grad_norm": 5.119288921356201, | |
| "learning_rate": 5.309835465003339e-06, | |
| "loss": 1.9364, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.643835616438356, | |
| "grad_norm": 6.177616596221924, | |
| "learning_rate": 5.054554913801255e-06, | |
| "loss": 1.8987, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.7123287671232876, | |
| "grad_norm": 5.89414644241333, | |
| "learning_rate": 4.7992743625991715e-06, | |
| "loss": 1.9352, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.7808219178082192, | |
| "grad_norm": 6.277669429779053, | |
| "learning_rate": 4.543993811397088e-06, | |
| "loss": 1.8815, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.8493150684931505, | |
| "grad_norm": 5.846259593963623, | |
| "learning_rate": 4.288713260195004e-06, | |
| "loss": 1.9424, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.9178082191780823, | |
| "grad_norm": 5.867184162139893, | |
| "learning_rate": 4.033432708992921e-06, | |
| "loss": 1.9088, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.9863013698630136, | |
| "grad_norm": 8.803180694580078, | |
| "learning_rate": 3.778152157790837e-06, | |
| "loss": 1.8713, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_classification_report": { | |
| "accuracy": 0.261, | |
| "ar": { | |
| "f1-score": 0.061946902654867256, | |
| "precision": 0.35, | |
| "recall": 0.03398058252427184, | |
| "support": 206.0 | |
| }, | |
| "cl": { | |
| "f1-score": 0.2, | |
| "precision": 0.1935483870967742, | |
| "recall": 0.20689655172413793, | |
| "support": 290.0 | |
| }, | |
| "co": { | |
| "f1-score": 0.30229007633587784, | |
| "precision": 0.27197802197802196, | |
| "recall": 0.3402061855670103, | |
| "support": 291.0 | |
| }, | |
| "es": { | |
| "f1-score": 0.32801161103047893, | |
| "precision": 0.275609756097561, | |
| "recall": 0.4050179211469534, | |
| "support": 279.0 | |
| }, | |
| "macro avg": { | |
| "f1-score": 0.23586615753847973, | |
| "precision": 0.28112434178245116, | |
| "recall": 0.2369581042839982, | |
| "support": 2000.0 | |
| }, | |
| "mx": { | |
| "f1-score": 0.272108843537415, | |
| "precision": 0.26936026936026936, | |
| "recall": 0.27491408934707906, | |
| "support": 291.0 | |
| }, | |
| "pe": { | |
| "f1-score": 0.2346368715083799, | |
| "precision": 0.1976470588235294, | |
| "recall": 0.28865979381443296, | |
| "support": 291.0 | |
| }, | |
| "pr": { | |
| "f1-score": 0.5088757396449705, | |
| "precision": 0.6323529411764706, | |
| "recall": 0.42574257425742573, | |
| "support": 101.0 | |
| }, | |
| "uy": { | |
| "f1-score": 0.21492537313432836, | |
| "precision": 0.33962264150943394, | |
| "recall": 0.1572052401746725, | |
| "support": 229.0 | |
| }, | |
| "ve": { | |
| "f1-score": 0.0, | |
| "precision": 0.0, | |
| "recall": 0.0, | |
| "support": 22.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.24916003843418816, | |
| "precision": 0.2809050615354289, | |
| "recall": 0.261, | |
| "support": 2000.0 | |
| } | |
| }, | |
| "eval_f1": 0.23586615753847973, | |
| "eval_loss": 1.9224119186401367, | |
| "eval_runtime": 3.5253, | |
| "eval_samples_per_second": 567.324, | |
| "eval_steps_per_second": 17.871, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 2.0547945205479454, | |
| "grad_norm": 6.486109733581543, | |
| "learning_rate": 3.5228716065887534e-06, | |
| "loss": 1.841, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.1232876712328768, | |
| "grad_norm": 6.070629596710205, | |
| "learning_rate": 3.26759105538667e-06, | |
| "loss": 1.8551, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.191780821917808, | |
| "grad_norm": 6.238626003265381, | |
| "learning_rate": 3.012310504184586e-06, | |
| "loss": 1.8897, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.26027397260274, | |
| "grad_norm": 6.827130317687988, | |
| "learning_rate": 2.7570299529825026e-06, | |
| "loss": 1.814, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.328767123287671, | |
| "grad_norm": 6.772587776184082, | |
| "learning_rate": 2.501749401780419e-06, | |
| "loss": 1.8214, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.3972602739726026, | |
| "grad_norm": 6.412906646728516, | |
| "learning_rate": 2.2464688505783353e-06, | |
| "loss": 1.8611, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.4657534246575343, | |
| "grad_norm": 6.432934284210205, | |
| "learning_rate": 1.9911882993762517e-06, | |
| "loss": 1.8398, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.5342465753424657, | |
| "grad_norm": 6.384337425231934, | |
| "learning_rate": 1.7359077481741683e-06, | |
| "loss": 1.8487, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.602739726027397, | |
| "grad_norm": 6.324769020080566, | |
| "learning_rate": 1.4806271969720847e-06, | |
| "loss": 1.8422, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.671232876712329, | |
| "grad_norm": 6.698541641235352, | |
| "learning_rate": 1.2253466457700013e-06, | |
| "loss": 1.8652, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.73972602739726, | |
| "grad_norm": 6.660873889923096, | |
| "learning_rate": 9.700660945679177e-07, | |
| "loss": 1.8213, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.808219178082192, | |
| "grad_norm": 6.92650032043457, | |
| "learning_rate": 7.147855433658339e-07, | |
| "loss": 1.847, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.8767123287671232, | |
| "grad_norm": 7.111581802368164, | |
| "learning_rate": 4.595049921637505e-07, | |
| "loss": 1.8672, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.9452054794520546, | |
| "grad_norm": 7.183070182800293, | |
| "learning_rate": 2.0422444096166686e-07, | |
| "loss": 1.8367, | |
| "step": 430 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 438, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 920815007980032.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |