| { | |
| "best_metric": 0.1991778548194697, | |
| "best_model_checkpoint": "/content/drive/MyDrive/model_outputs/trial_5/checkpoint-146", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 146, | |
| "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 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 306938335993344.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |