| { |
| "best_global_step": 525, |
| "best_metric": 0.8338557993730408, |
| "best_model_checkpoint": "./lettuce_ft/checkpoint-525", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 525, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.19047619047619047, |
| "grad_norm": 0.7677925825119019, |
| "learning_rate": 7.600000000000001e-06, |
| "loss": 0.19512724876403809, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.38095238095238093, |
| "grad_norm": 0.23630067706108093, |
| "learning_rate": 1.5600000000000003e-05, |
| "loss": 0.15847638845443726, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.6374622583389282, |
| "learning_rate": 1.9689655172413796e-05, |
| "loss": 0.20727028846740722, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.7619047619047619, |
| "grad_norm": 0.8266599178314209, |
| "learning_rate": 1.9e-05, |
| "loss": 0.18287111520767213, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.9523809523809523, |
| "grad_norm": 0.6583699584007263, |
| "learning_rate": 1.831034482758621e-05, |
| "loss": 0.12251497507095337, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.7323615160349854, |
| "eval_loss": 0.11771774291992188, |
| "eval_precision": 0.988976377952756, |
| "eval_recall": 0.5814814814814815, |
| "eval_runtime": 20.0131, |
| "eval_samples_per_second": 8.994, |
| "eval_steps_per_second": 2.249, |
| "step": 105 |
| }, |
| { |
| "epoch": 1.1428571428571428, |
| "grad_norm": 0.5870521664619446, |
| "learning_rate": 1.7620689655172414e-05, |
| "loss": 0.12844752073287963, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 1.8096352815628052, |
| "learning_rate": 1.6931034482758623e-05, |
| "loss": 0.14761706590652465, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.5238095238095237, |
| "grad_norm": 0.42143744230270386, |
| "learning_rate": 1.6241379310344828e-05, |
| "loss": 0.10572866201400757, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.7142857142857144, |
| "grad_norm": 1.1219831705093384, |
| "learning_rate": 1.5551724137931036e-05, |
| "loss": 0.08384537696838379, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.9047619047619047, |
| "grad_norm": 0.8192638158798218, |
| "learning_rate": 1.4862068965517243e-05, |
| "loss": 0.1669264554977417, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.7592997811816192, |
| "eval_loss": 0.09724947810173035, |
| "eval_precision": 0.9278074866310161, |
| "eval_recall": 0.6425925925925926, |
| "eval_runtime": 19.9967, |
| "eval_samples_per_second": 9.001, |
| "eval_steps_per_second": 2.25, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.0952380952380953, |
| "grad_norm": 0.6344627141952515, |
| "learning_rate": 1.417241379310345e-05, |
| "loss": 0.08497620224952698, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.2857142857142856, |
| "grad_norm": 0.5775904655456543, |
| "learning_rate": 1.3482758620689656e-05, |
| "loss": 0.08870592713356018, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.4761904761904763, |
| "grad_norm": 0.49520859122276306, |
| "learning_rate": 1.2793103448275863e-05, |
| "loss": 0.08883096575737, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.6666666666666665, |
| "grad_norm": 1.1992110013961792, |
| "learning_rate": 1.2103448275862071e-05, |
| "loss": 0.08080946207046509, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.857142857142857, |
| "grad_norm": 1.4169745445251465, |
| "learning_rate": 1.1413793103448276e-05, |
| "loss": 0.07005050182342529, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.8050982474774296, |
| "eval_loss": 0.08078155666589737, |
| "eval_precision": 0.9439601494396015, |
| "eval_recall": 0.7018518518518518, |
| "eval_runtime": 20.0961, |
| "eval_samples_per_second": 8.957, |
| "eval_steps_per_second": 2.239, |
| "step": 315 |
| }, |
| { |
| "epoch": 3.0476190476190474, |
| "grad_norm": 0.8966546058654785, |
| "learning_rate": 1.0724137931034484e-05, |
| "loss": 0.06641889810562134, |
| "step": 320 |
| }, |
| { |
| "epoch": 3.238095238095238, |
| "grad_norm": 0.5824030041694641, |
| "learning_rate": 1.003448275862069e-05, |
| "loss": 0.05119739174842834, |
| "step": 340 |
| }, |
| { |
| "epoch": 3.4285714285714284, |
| "grad_norm": 0.6942387223243713, |
| "learning_rate": 9.344827586206898e-06, |
| "loss": 0.04003562927246094, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.619047619047619, |
| "grad_norm": 0.5906447172164917, |
| "learning_rate": 8.655172413793104e-06, |
| "loss": 0.04091911017894745, |
| "step": 380 |
| }, |
| { |
| "epoch": 3.8095238095238093, |
| "grad_norm": 0.3436790704727173, |
| "learning_rate": 7.965517241379311e-06, |
| "loss": 0.04960331916809082, |
| "step": 400 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.3449792265892029, |
| "learning_rate": 7.275862068965518e-06, |
| "loss": 0.03436199724674225, |
| "step": 420 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_f1": 0.8254963427377221, |
| "eval_loss": 0.07085700333118439, |
| "eval_precision": 0.947242206235012, |
| "eval_recall": 0.7314814814814815, |
| "eval_runtime": 20.0966, |
| "eval_samples_per_second": 8.957, |
| "eval_steps_per_second": 2.239, |
| "step": 420 |
| }, |
| { |
| "epoch": 4.190476190476191, |
| "grad_norm": 0.511233389377594, |
| "learning_rate": 6.586206896551724e-06, |
| "loss": 0.03371661007404327, |
| "step": 440 |
| }, |
| { |
| "epoch": 4.380952380952381, |
| "grad_norm": 0.4449719786643982, |
| "learning_rate": 5.896551724137931e-06, |
| "loss": 0.0406580239534378, |
| "step": 460 |
| }, |
| { |
| "epoch": 4.571428571428571, |
| "grad_norm": 0.3001626133918762, |
| "learning_rate": 5.206896551724139e-06, |
| "loss": 0.025170013308525085, |
| "step": 480 |
| }, |
| { |
| "epoch": 4.761904761904762, |
| "grad_norm": 0.4409080743789673, |
| "learning_rate": 4.517241379310345e-06, |
| "loss": 0.03046942949295044, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.9523809523809526, |
| "grad_norm": 0.1583988219499588, |
| "learning_rate": 3.827586206896552e-06, |
| "loss": 0.020532441139221192, |
| "step": 520 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_f1": 0.8338557993730408, |
| "eval_loss": 0.07030046731233597, |
| "eval_precision": 0.9568345323741008, |
| "eval_recall": 0.7388888888888889, |
| "eval_runtime": 20.4927, |
| "eval_samples_per_second": 8.784, |
| "eval_steps_per_second": 2.196, |
| "step": 525 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 630, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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": 5724731813068800.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
