| { | |
| "best_metric": 0.2753944289993962, | |
| "best_model_checkpoint": "/content/drive/MyDrive/model_outputs/trial_1/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": 6.121810436248779, | |
| "learning_rate": 2.3746770222327703e-05, | |
| "loss": 2.1931, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.136986301369863, | |
| "grad_norm": 5.8526291847229, | |
| "learning_rate": 4.254064265542705e-05, | |
| "loss": 2.0753, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2054794520547945, | |
| "grad_norm": 5.28399133682251, | |
| "learning_rate": 4.152292393161301e-05, | |
| "loss": 2.1135, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 4.682084083557129, | |
| "learning_rate": 4.050520520779896e-05, | |
| "loss": 2.0526, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3424657534246575, | |
| "grad_norm": 4.155479907989502, | |
| "learning_rate": 3.948748648398492e-05, | |
| "loss": 1.9939, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.410958904109589, | |
| "grad_norm": 4.142167568206787, | |
| "learning_rate": 3.8469767760170876e-05, | |
| "loss": 2.0411, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4794520547945205, | |
| "grad_norm": 4.870395660400391, | |
| "learning_rate": 3.745204903635683e-05, | |
| "loss": 2.0127, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.547945205479452, | |
| "grad_norm": 4.938784122467041, | |
| "learning_rate": 3.6434330312542784e-05, | |
| "loss": 1.9952, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6164383561643836, | |
| "grad_norm": 4.4871931076049805, | |
| "learning_rate": 3.5416611588728745e-05, | |
| "loss": 1.9433, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.684931506849315, | |
| "grad_norm": 4.6226115226745605, | |
| "learning_rate": 3.43988928649147e-05, | |
| "loss": 1.9699, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7534246575342466, | |
| "grad_norm": 5.69040060043335, | |
| "learning_rate": 3.338117414110065e-05, | |
| "loss": 1.894, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.821917808219178, | |
| "grad_norm": 5.492514610290527, | |
| "learning_rate": 3.236345541728661e-05, | |
| "loss": 1.9948, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8904109589041096, | |
| "grad_norm": 6.370945930480957, | |
| "learning_rate": 3.134573669347256e-05, | |
| "loss": 1.9392, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.958904109589041, | |
| "grad_norm": 6.988052845001221, | |
| "learning_rate": 3.0328017969658522e-05, | |
| "loss": 1.9294, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_classification_report": { | |
| "accuracy": 0.2985, | |
| "ar": { | |
| "f1-score": 0.23369565217391305, | |
| "precision": 0.2654320987654321, | |
| "recall": 0.2087378640776699, | |
| "support": 206.0 | |
| }, | |
| "cl": { | |
| "f1-score": 0.25153374233128833, | |
| "precision": 0.2265193370165746, | |
| "recall": 0.2827586206896552, | |
| "support": 290.0 | |
| }, | |
| "co": { | |
| "f1-score": 0.3475409836065574, | |
| "precision": 0.3322884012539185, | |
| "recall": 0.3642611683848797, | |
| "support": 291.0 | |
| }, | |
| "es": { | |
| "f1-score": 0.3899018232819074, | |
| "precision": 0.32027649769585254, | |
| "recall": 0.4982078853046595, | |
| "support": 279.0 | |
| }, | |
| "macro avg": { | |
| "f1-score": 0.2753944289993962, | |
| "precision": 0.3140605088159512, | |
| "recall": 0.2836608687859575, | |
| "support": 2000.0 | |
| }, | |
| "mx": { | |
| "f1-score": 0.29961089494163423, | |
| "precision": 0.3452914798206278, | |
| "recall": 0.2646048109965636, | |
| "support": 291.0 | |
| }, | |
| "pe": { | |
| "f1-score": 0.09202453987730061, | |
| "precision": 0.42857142857142855, | |
| "recall": 0.05154639175257732, | |
| "support": 291.0 | |
| }, | |
| "pr": { | |
| "f1-score": 0.5988700564971752, | |
| "precision": 0.6973684210526315, | |
| "recall": 0.5247524752475248, | |
| "support": 101.0 | |
| }, | |
| "uy": { | |
| "f1-score": 0.26537216828478966, | |
| "precision": 0.21079691516709512, | |
| "recall": 0.35807860262008734, | |
| "support": 229.0 | |
| }, | |
| "ve": { | |
| "f1-score": 0.0, | |
| "precision": 0.0, | |
| "recall": 0.0, | |
| "support": 22.0 | |
| }, | |
| "weighted avg": { | |
| "f1-score": 0.28311256916240085, | |
| "precision": 0.32516174907209394, | |
| "recall": 0.2985, | |
| "support": 2000.0 | |
| } | |
| }, | |
| "eval_f1": 0.2753944289993962, | |
| "eval_loss": 1.8665934801101685, | |
| "eval_runtime": 2.1391, | |
| "eval_samples_per_second": 934.98, | |
| "eval_steps_per_second": 29.452, | |
| "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": 153469167996672.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |