| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 3510, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "eval_f1": 0.3722687284743791, | |
| "eval_loss": 1.3361328840255737, | |
| "eval_runtime": 3.2985, | |
| "eval_samples_per_second": 29.71, | |
| "eval_steps_per_second": 29.71, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_f1": 0.4344699929794222, | |
| "eval_loss": 1.1836130619049072, | |
| "eval_runtime": 3.274, | |
| "eval_samples_per_second": 29.933, | |
| "eval_steps_per_second": 29.933, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_f1": 0.3996935122704078, | |
| "eval_loss": 1.1635534763336182, | |
| "eval_runtime": 3.2772, | |
| "eval_samples_per_second": 29.904, | |
| "eval_steps_per_second": 29.904, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_f1": 0.5028054395723479, | |
| "eval_loss": 1.353499174118042, | |
| "eval_runtime": 3.2926, | |
| "eval_samples_per_second": 29.764, | |
| "eval_steps_per_second": 29.764, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.572649572649573e-05, | |
| "loss": 1.2064, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_f1": 0.47071964928887344, | |
| "eval_loss": 1.2940737009048462, | |
| "eval_runtime": 3.3744, | |
| "eval_samples_per_second": 29.042, | |
| "eval_steps_per_second": 29.042, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_f1": 0.49370416278560797, | |
| "eval_loss": 1.2891041040420532, | |
| "eval_runtime": 3.3094, | |
| "eval_samples_per_second": 29.613, | |
| "eval_steps_per_second": 29.613, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.47736617527595926, | |
| "eval_loss": 1.2047343254089355, | |
| "eval_runtime": 3.3145, | |
| "eval_samples_per_second": 29.567, | |
| "eval_steps_per_second": 29.567, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_f1": 0.4943830125990876, | |
| "eval_loss": 1.2190661430358887, | |
| "eval_runtime": 3.3377, | |
| "eval_samples_per_second": 29.362, | |
| "eval_steps_per_second": 29.362, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_f1": 0.4777863203104454, | |
| "eval_loss": 1.174961805343628, | |
| "eval_runtime": 3.3391, | |
| "eval_samples_per_second": 29.349, | |
| "eval_steps_per_second": 29.349, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.1452991452991456e-05, | |
| "loss": 0.9207, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_f1": 0.49086129207075757, | |
| "eval_loss": 1.3087153434753418, | |
| "eval_runtime": 3.4003, | |
| "eval_samples_per_second": 28.821, | |
| "eval_steps_per_second": 28.821, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_f1": 0.49757882395260544, | |
| "eval_loss": 1.2435556650161743, | |
| "eval_runtime": 3.4366, | |
| "eval_samples_per_second": 28.517, | |
| "eval_steps_per_second": 28.517, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_f1": 0.503327058221218, | |
| "eval_loss": 1.1465363502502441, | |
| "eval_runtime": 3.2944, | |
| "eval_samples_per_second": 29.748, | |
| "eval_steps_per_second": 29.748, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_f1": 0.5141589868888157, | |
| "eval_loss": 1.113364577293396, | |
| "eval_runtime": 3.3642, | |
| "eval_samples_per_second": 29.131, | |
| "eval_steps_per_second": 29.131, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_f1": 0.5383469405673188, | |
| "eval_loss": 1.1939647197723389, | |
| "eval_runtime": 3.3033, | |
| "eval_samples_per_second": 29.668, | |
| "eval_steps_per_second": 29.668, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.7179487179487178e-05, | |
| "loss": 0.8149, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_f1": 0.5291030100787034, | |
| "eval_loss": 1.2552497386932373, | |
| "eval_runtime": 3.7541, | |
| "eval_samples_per_second": 26.105, | |
| "eval_steps_per_second": 26.105, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_f1": 0.5259736412492381, | |
| "eval_loss": 1.3746747970581055, | |
| "eval_runtime": 4.9995, | |
| "eval_samples_per_second": 19.602, | |
| "eval_steps_per_second": 19.602, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "eval_f1": 0.5329388682083431, | |
| "eval_loss": 1.3680145740509033, | |
| "eval_runtime": 5.1597, | |
| "eval_samples_per_second": 18.993, | |
| "eval_steps_per_second": 18.993, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_f1": 0.5189920532535025, | |
| "eval_loss": 1.27865469455719, | |
| "eval_runtime": 5.0223, | |
| "eval_samples_per_second": 19.513, | |
| "eval_steps_per_second": 19.513, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "eval_f1": 0.5409205239275264, | |
| "eval_loss": 1.3888845443725586, | |
| "eval_runtime": 3.3132, | |
| "eval_samples_per_second": 29.579, | |
| "eval_steps_per_second": 29.579, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 1.2905982905982905e-05, | |
| "loss": 0.6152, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_f1": 0.543504294934508, | |
| "eval_loss": 1.3602004051208496, | |
| "eval_runtime": 3.3336, | |
| "eval_samples_per_second": 29.398, | |
| "eval_steps_per_second": 29.398, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_f1": 0.5467811408362643, | |
| "eval_loss": 1.3174574375152588, | |
| "eval_runtime": 5.0569, | |
| "eval_samples_per_second": 19.379, | |
| "eval_steps_per_second": 19.379, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_f1": 0.5365057187973831, | |
| "eval_loss": 1.5886870622634888, | |
| "eval_runtime": 4.5058, | |
| "eval_samples_per_second": 21.75, | |
| "eval_steps_per_second": 21.75, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "eval_f1": 0.5563382534701277, | |
| "eval_loss": 1.517231822013855, | |
| "eval_runtime": 4.5269, | |
| "eval_samples_per_second": 21.648, | |
| "eval_steps_per_second": 21.648, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 3.42, | |
| "eval_f1": 0.5661390498930103, | |
| "eval_loss": 1.5470443964004517, | |
| "eval_runtime": 3.6905, | |
| "eval_samples_per_second": 26.555, | |
| "eval_steps_per_second": 26.555, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 8.632478632478633e-06, | |
| "loss": 0.4719, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_f1": 0.521216772952552, | |
| "eval_loss": 1.4928430318832397, | |
| "eval_runtime": 3.3155, | |
| "eval_samples_per_second": 29.558, | |
| "eval_steps_per_second": 29.558, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "eval_f1": 0.5356457612585566, | |
| "eval_loss": 1.6497721672058105, | |
| "eval_runtime": 4.8518, | |
| "eval_samples_per_second": 20.199, | |
| "eval_steps_per_second": 20.199, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "eval_f1": 0.5596834952223371, | |
| "eval_loss": 1.4976708889007568, | |
| "eval_runtime": 4.6972, | |
| "eval_samples_per_second": 20.863, | |
| "eval_steps_per_second": 20.863, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "eval_f1": 0.5470066167039311, | |
| "eval_loss": 1.471981167793274, | |
| "eval_runtime": 4.5019, | |
| "eval_samples_per_second": 21.769, | |
| "eval_steps_per_second": 21.769, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_f1": 0.5492964393504802, | |
| "eval_loss": 1.5796676874160767, | |
| "eval_runtime": 4.7041, | |
| "eval_samples_per_second": 20.833, | |
| "eval_steps_per_second": 20.833, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 4.358974358974359e-06, | |
| "loss": 0.372, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "eval_f1": 0.5445354826532323, | |
| "eval_loss": 1.6874395608901978, | |
| "eval_runtime": 3.9793, | |
| "eval_samples_per_second": 24.628, | |
| "eval_steps_per_second": 24.628, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "eval_f1": 0.5544723066439012, | |
| "eval_loss": 1.6702477931976318, | |
| "eval_runtime": 4.7443, | |
| "eval_samples_per_second": 20.656, | |
| "eval_steps_per_second": 20.656, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 4.56, | |
| "eval_f1": 0.5469058666319371, | |
| "eval_loss": 1.7671833038330078, | |
| "eval_runtime": 4.6665, | |
| "eval_samples_per_second": 21.001, | |
| "eval_steps_per_second": 21.001, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "eval_f1": 0.5485370297299399, | |
| "eval_loss": 1.7351080179214478, | |
| "eval_runtime": 4.8851, | |
| "eval_samples_per_second": 20.061, | |
| "eval_steps_per_second": 20.061, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "eval_f1": 0.5497797755164764, | |
| "eval_loss": 1.7282612323760986, | |
| "eval_runtime": 5.1791, | |
| "eval_samples_per_second": 18.922, | |
| "eval_steps_per_second": 18.922, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "learning_rate": 8.547008547008547e-08, | |
| "loss": 0.2944, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_f1": 0.5503861750639598, | |
| "eval_loss": 1.698703408241272, | |
| "eval_runtime": 5.6701, | |
| "eval_samples_per_second": 17.284, | |
| "eval_steps_per_second": 17.284, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 3510, | |
| "total_flos": 2890172619430200.0, | |
| "train_loss": 0.6695007115008145, | |
| "train_runtime": 916.4977, | |
| "train_samples_per_second": 3.83, | |
| "train_steps_per_second": 3.83 | |
| } | |
| ], | |
| "max_steps": 3510, | |
| "num_train_epochs": 5, | |
| "total_flos": 2890172619430200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |