| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.3289365210222588, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026380873866446827, | |
| "grad_norm": 1.777541995048523, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4185, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026380873866446827, | |
| "eval_loss": 3.623441457748413, | |
| "eval_runtime": 1.1406, | |
| "eval_samples_per_second": 43.838, | |
| "eval_steps_per_second": 11.398, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05276174773289365, | |
| "grad_norm": 2.632246255874634, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7331, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07914262159934048, | |
| "grad_norm": 2.883641004562378, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.8645, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1055234954657873, | |
| "grad_norm": 2.4836220741271973, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.5391, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13190436933223412, | |
| "grad_norm": 2.5708866119384766, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.4391, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15828524319868095, | |
| "grad_norm": 2.931725263595581, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.3818, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18466611706512778, | |
| "grad_norm": 2.899811267852783, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.4126, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2110469909315746, | |
| "grad_norm": 3.1962263584136963, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4357, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23742786479802144, | |
| "grad_norm": 4.456316947937012, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.7543, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.26380873866446825, | |
| "grad_norm": 2.725989818572998, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.7691, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2901896125309151, | |
| "grad_norm": 2.840864896774292, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.2073, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3165704863973619, | |
| "grad_norm": 2.4223415851593018, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.0719, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.34295136026380874, | |
| "grad_norm": 1.9131155014038086, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.0024, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.36933223413025557, | |
| "grad_norm": 1.920853853225708, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.9629, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3957131079967024, | |
| "grad_norm": 1.7250676155090332, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.1086, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4220939818631492, | |
| "grad_norm": 1.8188282251358032, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.0697, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.44847485572959606, | |
| "grad_norm": 1.8869132995605469, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.1263, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4748557295960429, | |
| "grad_norm": 3.000149965286255, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2637, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5012366034624897, | |
| "grad_norm": 2.330080270767212, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1939, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5276174773289365, | |
| "grad_norm": 1.816513180732727, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.6319, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5539983511953833, | |
| "grad_norm": 1.4163626432418823, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4592, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5803792250618302, | |
| "grad_norm": 1.3975715637207031, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.4425, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.606760098928277, | |
| "grad_norm": 1.2029556035995483, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4378, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6331409727947238, | |
| "grad_norm": 1.521054744720459, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4887, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6595218466611706, | |
| "grad_norm": 2.3948323726654053, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.5964, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6595218466611706, | |
| "eval_loss": 0.5060842037200928, | |
| "eval_runtime": 1.1542, | |
| "eval_samples_per_second": 43.32, | |
| "eval_steps_per_second": 11.263, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6859027205276175, | |
| "grad_norm": 2.5826122760772705, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6125, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7122835943940643, | |
| "grad_norm": 3.505153179168701, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6932, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7386644682605111, | |
| "grad_norm": 2.812425136566162, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.6941, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.765045342126958, | |
| "grad_norm": 2.6993019580841064, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.5275, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7914262159934048, | |
| "grad_norm": 1.6319504976272583, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1855, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8178070898598516, | |
| "grad_norm": 1.3986767530441284, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.1984, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8441879637262985, | |
| "grad_norm": 1.2282105684280396, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.209, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8705688375927453, | |
| "grad_norm": 0.9565277695655823, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.1846, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8969497114591921, | |
| "grad_norm": 1.4811856746673584, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.2668, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9233305853256389, | |
| "grad_norm": 1.6929315328598022, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.3288, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9497114591920858, | |
| "grad_norm": 2.3932266235351562, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4036, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9760923330585326, | |
| "grad_norm": 3.5589423179626465, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.4499, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.012366034624897, | |
| "grad_norm": 2.737474203109741, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.4322, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0387469084913439, | |
| "grad_norm": 1.1250501871109009, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.1337, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0651277823577905, | |
| "grad_norm": 0.7960028052330017, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.085, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0915086562242373, | |
| "grad_norm": 1.7320730686187744, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.0977, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.1178895300906841, | |
| "grad_norm": 1.0344929695129395, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.083, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.144270403957131, | |
| "grad_norm": 1.1064660549163818, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.1348, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1706512778235778, | |
| "grad_norm": 1.4996426105499268, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.1599, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.1970321516900246, | |
| "grad_norm": 1.5553085803985596, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.2289, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2234130255564715, | |
| "grad_norm": 2.5401673316955566, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.3329, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2497938994229183, | |
| "grad_norm": 2.7614471912384033, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.2996, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.2761747732893651, | |
| "grad_norm": 2.3601768016815186, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.1815, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.302555647155812, | |
| "grad_norm": 0.7562735080718994, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0601, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3289365210222588, | |
| "grad_norm": 0.7278848886489868, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0562, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3289365210222588, | |
| "eval_loss": 0.14836329221725464, | |
| "eval_runtime": 1.1577, | |
| "eval_samples_per_second": 43.188, | |
| "eval_steps_per_second": 11.229, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.059536353886208e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |