| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.44251703690592087, | |
| "eval_steps": 500, | |
| "global_step": 5000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008850340738118417, | |
| "grad_norm": 1.517469048500061, | |
| "learning_rate": 1.9919999999999997e-06, | |
| "loss": 1.519, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.017700681476236834, | |
| "grad_norm": 1.6662976741790771, | |
| "learning_rate": 1.984e-06, | |
| "loss": 1.4776, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.026551022214355253, | |
| "grad_norm": 0.8021761775016785, | |
| "learning_rate": 1.976e-06, | |
| "loss": 1.4026, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.03540136295247367, | |
| "grad_norm": 0.8772447109222412, | |
| "learning_rate": 1.968e-06, | |
| "loss": 1.3306, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04425170369059209, | |
| "grad_norm": 0.4179963767528534, | |
| "learning_rate": 1.96e-06, | |
| "loss": 1.286, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.053102044428710506, | |
| "grad_norm": 0.4829399287700653, | |
| "learning_rate": 1.9519999999999997e-06, | |
| "loss": 1.2756, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.061952385166828924, | |
| "grad_norm": 0.5651261806488037, | |
| "learning_rate": 1.944e-06, | |
| "loss": 1.2721, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.07080272590494734, | |
| "grad_norm": 0.5160872936248779, | |
| "learning_rate": 1.9359999999999998e-06, | |
| "loss": 1.2579, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.07965306664306576, | |
| "grad_norm": 0.7501122355461121, | |
| "learning_rate": 1.928e-06, | |
| "loss": 1.2853, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.08850340738118417, | |
| "grad_norm": 0.591393232345581, | |
| "learning_rate": 1.92e-06, | |
| "loss": 1.2472, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0973537481193026, | |
| "grad_norm": 0.5573005080223083, | |
| "learning_rate": 1.9119999999999997e-06, | |
| "loss": 1.2348, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.10620408885742101, | |
| "grad_norm": 0.607552707195282, | |
| "learning_rate": 1.904e-06, | |
| "loss": 1.2679, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.11505442959553942, | |
| "grad_norm": 0.6899151802062988, | |
| "learning_rate": 1.8959999999999997e-06, | |
| "loss": 1.2513, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.12390477033365785, | |
| "grad_norm": 0.5849478244781494, | |
| "learning_rate": 1.8879999999999998e-06, | |
| "loss": 1.226, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.13275511107177626, | |
| "grad_norm": 0.6027043461799622, | |
| "learning_rate": 1.8799999999999998e-06, | |
| "loss": 1.2163, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.14160545180989467, | |
| "grad_norm": 0.6785966157913208, | |
| "learning_rate": 1.872e-06, | |
| "loss": 1.2076, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.1504557925480131, | |
| "grad_norm": 0.5975379347801208, | |
| "learning_rate": 1.864e-06, | |
| "loss": 1.2146, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.15930613328613152, | |
| "grad_norm": 0.685453474521637, | |
| "learning_rate": 1.856e-06, | |
| "loss": 1.198, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.16815647402424994, | |
| "grad_norm": 1.1250847578048706, | |
| "learning_rate": 1.848e-06, | |
| "loss": 1.218, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.17700681476236835, | |
| "grad_norm": 0.6129019260406494, | |
| "learning_rate": 1.84e-06, | |
| "loss": 1.1894, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.18585715550048676, | |
| "grad_norm": 0.7388463616371155, | |
| "learning_rate": 1.832e-06, | |
| "loss": 1.1962, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.1947074962386052, | |
| "grad_norm": 0.5909475684165955, | |
| "learning_rate": 1.824e-06, | |
| "loss": 1.241, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.2035578369767236, | |
| "grad_norm": 0.5264613032341003, | |
| "learning_rate": 1.816e-06, | |
| "loss": 1.1915, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.21240817771484202, | |
| "grad_norm": 0.6419306397438049, | |
| "learning_rate": 1.8079999999999999e-06, | |
| "loss": 1.1938, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.22125851845296043, | |
| "grad_norm": 0.6240788698196411, | |
| "learning_rate": 1.8e-06, | |
| "loss": 1.214, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.23010885919107885, | |
| "grad_norm": 0.7954173684120178, | |
| "learning_rate": 1.792e-06, | |
| "loss": 1.195, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.23895919992919729, | |
| "grad_norm": 0.7451553344726562, | |
| "learning_rate": 1.784e-06, | |
| "loss": 1.1793, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.2478095406673157, | |
| "grad_norm": 0.8471085429191589, | |
| "learning_rate": 1.776e-06, | |
| "loss": 1.1895, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.2566598814054341, | |
| "grad_norm": 1.0085513591766357, | |
| "learning_rate": 1.7679999999999998e-06, | |
| "loss": 1.2087, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.2655102221435525, | |
| "grad_norm": 0.7709102630615234, | |
| "learning_rate": 1.7599999999999999e-06, | |
| "loss": 1.1959, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.27436056288167093, | |
| "grad_norm": 0.7612162232398987, | |
| "learning_rate": 1.752e-06, | |
| "loss": 1.1803, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.28321090361978934, | |
| "grad_norm": 1.0669310092926025, | |
| "learning_rate": 1.744e-06, | |
| "loss": 1.1548, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.29206124435790776, | |
| "grad_norm": 0.7489383220672607, | |
| "learning_rate": 1.736e-06, | |
| "loss": 1.1654, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.3009115850960262, | |
| "grad_norm": 0.8011970520019531, | |
| "learning_rate": 1.7279999999999998e-06, | |
| "loss": 1.1789, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.30976192583414464, | |
| "grad_norm": 0.7374864816665649, | |
| "learning_rate": 1.7199999999999998e-06, | |
| "loss": 1.171, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.31861226657226305, | |
| "grad_norm": 0.8267546892166138, | |
| "learning_rate": 1.7119999999999999e-06, | |
| "loss": 1.1435, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.32746260731038146, | |
| "grad_norm": 0.8837570548057556, | |
| "learning_rate": 1.704e-06, | |
| "loss": 1.1674, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.33631294804849987, | |
| "grad_norm": 0.7216938138008118, | |
| "learning_rate": 1.696e-06, | |
| "loss": 1.1446, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.3451632887866183, | |
| "grad_norm": 0.8478527069091797, | |
| "learning_rate": 1.6879999999999998e-06, | |
| "loss": 1.1721, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.3540136295247367, | |
| "grad_norm": 0.8281861543655396, | |
| "learning_rate": 1.6799999999999998e-06, | |
| "loss": 1.1741, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.3628639702628551, | |
| "grad_norm": 0.6918274760246277, | |
| "learning_rate": 1.6719999999999998e-06, | |
| "loss": 1.1433, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.3717143110009735, | |
| "grad_norm": 0.6722283363342285, | |
| "learning_rate": 1.6639999999999999e-06, | |
| "loss": 1.189, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.38056465173909193, | |
| "grad_norm": 0.8337692022323608, | |
| "learning_rate": 1.656e-06, | |
| "loss": 1.1694, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.3894149924772104, | |
| "grad_norm": 0.7980256080627441, | |
| "learning_rate": 1.648e-06, | |
| "loss": 1.1794, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.3982653332153288, | |
| "grad_norm": 0.9903015494346619, | |
| "learning_rate": 1.6399999999999998e-06, | |
| "loss": 1.2027, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4071156739534472, | |
| "grad_norm": 0.7119297385215759, | |
| "learning_rate": 1.6319999999999998e-06, | |
| "loss": 1.1638, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.41596601469156563, | |
| "grad_norm": 0.9170375466346741, | |
| "learning_rate": 1.624e-06, | |
| "loss": 1.1706, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.42481635542968404, | |
| "grad_norm": 0.7098402976989746, | |
| "learning_rate": 1.616e-06, | |
| "loss": 1.1738, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.43366669616780246, | |
| "grad_norm": 0.9326470494270325, | |
| "learning_rate": 1.608e-06, | |
| "loss": 1.1526, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.44251703690592087, | |
| "grad_norm": 0.7765191197395325, | |
| "learning_rate": 1.6e-06, | |
| "loss": 1.1687, | |
| "step": 5000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 25000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.916766417699275e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |