| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.20640289467474238, | |
| "eval_steps": 25, | |
| "global_step": 41, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0050342169432864, | |
| "grad_norm": 0.48587390780448914, | |
| "learning_rate": 0.00015, | |
| "loss": 0.9906, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0050342169432864, | |
| "eval_loss": 2.508871555328369, | |
| "eval_runtime": 1.5207, | |
| "eval_samples_per_second": 32.88, | |
| "eval_steps_per_second": 8.549, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0100684338865728, | |
| "grad_norm": 0.5944941639900208, | |
| "learning_rate": 0.0003, | |
| "loss": 1.2733, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0151026508298592, | |
| "grad_norm": 0.9103966951370239, | |
| "learning_rate": 0.00029956223659811834, | |
| "loss": 1.5659, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0201368677731456, | |
| "grad_norm": 1.8556902408599854, | |
| "learning_rate": 0.0002982517854561182, | |
| "loss": 1.5236, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025171084716432, | |
| "grad_norm": 2.2436363697052, | |
| "learning_rate": 0.00029607714535251703, | |
| "loss": 1.1616, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0302053016597184, | |
| "grad_norm": 1.5221978425979614, | |
| "learning_rate": 0.0002930524196628646, | |
| "loss": 0.9301, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.035239518603004796, | |
| "grad_norm": 1.870839238166809, | |
| "learning_rate": 0.00028919722489394124, | |
| "loss": 0.6809, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0402737355462912, | |
| "grad_norm": 2.2418909072875977, | |
| "learning_rate": 0.0002845365634631833, | |
| "loss": 0.5609, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0453079524895776, | |
| "grad_norm": 1.7868170738220215, | |
| "learning_rate": 0.00027910066154841225, | |
| "loss": 0.5075, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.050342169432864, | |
| "grad_norm": 1.003621220588684, | |
| "learning_rate": 0.0002729247730594727, | |
| "loss": 0.4796, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.055376386376150395, | |
| "grad_norm": 1.2910493612289429, | |
| "learning_rate": 0.0002660489510030986, | |
| "loss": 0.3807, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0604106033194368, | |
| "grad_norm": 0.7100380659103394, | |
| "learning_rate": 0.0002585177877237959, | |
| "loss": 0.2717, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06544482026272319, | |
| "grad_norm": 1.3275943994522095, | |
| "learning_rate": 0.0002503801257053759, | |
| "loss": 0.3117, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07047903720600959, | |
| "grad_norm": 0.6264938712120056, | |
| "learning_rate": 0.000241688740808706, | |
| "loss": 0.2476, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.075513254149296, | |
| "grad_norm": 0.36277681589126587, | |
| "learning_rate": 0.00023249999999999999, | |
| "loss": 0.2302, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0805474710925824, | |
| "grad_norm": 0.3652091920375824, | |
| "learning_rate": 0.0002228734957894123, | |
| "loss": 0.2193, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0855816880358688, | |
| "grad_norm": 0.35171782970428467, | |
| "learning_rate": 0.0002128716597507423, | |
| "loss": 0.2939, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0906159049791552, | |
| "grad_norm": 0.3776039183139801, | |
| "learning_rate": 0.0002025593576287211, | |
| "loss": 0.2786, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0956501219224416, | |
| "grad_norm": 0.37664252519607544, | |
| "learning_rate": 0.000192003468659766, | |
| "loss": 0.2947, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.100684338865728, | |
| "grad_norm": 0.37431633472442627, | |
| "learning_rate": 0.00018127245183446858, | |
| "loss": 0.2878, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10571855580901439, | |
| "grad_norm": 0.3799932897090912, | |
| "learning_rate": 0.00017043590191477103, | |
| "loss": 0.3062, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11075277275230079, | |
| "grad_norm": 0.34425467252731323, | |
| "learning_rate": 0.000159564098085229, | |
| "loss": 0.3438, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11578698969558719, | |
| "grad_norm": 0.3520929217338562, | |
| "learning_rate": 0.00014872754816553141, | |
| "loss": 0.3027, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1208212066388736, | |
| "grad_norm": 0.31669244170188904, | |
| "learning_rate": 0.00013799653134023403, | |
| "loss": 0.2363, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12585542358215998, | |
| "grad_norm": 0.4543594717979431, | |
| "learning_rate": 0.00012744064237127888, | |
| "loss": 0.2623, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12585542358215998, | |
| "eval_loss": 0.20168980956077576, | |
| "eval_runtime": 1.5239, | |
| "eval_samples_per_second": 32.81, | |
| "eval_steps_per_second": 8.531, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13088964052544638, | |
| "grad_norm": 0.2247937023639679, | |
| "learning_rate": 0.00011712834024925766, | |
| "loss": 0.1669, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13592385746873278, | |
| "grad_norm": 0.25750628113746643, | |
| "learning_rate": 0.00010712650421058767, | |
| "loss": 0.1826, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14095807441201919, | |
| "grad_norm": 0.24032293260097504, | |
| "learning_rate": 9.750000000000003e-05, | |
| "loss": 0.2098, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1459922913553056, | |
| "grad_norm": 0.27641579508781433, | |
| "learning_rate": 8.831125919129397e-05, | |
| "loss": 0.1883, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.151026508298592, | |
| "grad_norm": 0.30863824486732483, | |
| "learning_rate": 7.961987429462408e-05, | |
| "loss": 0.2644, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1560607252418784, | |
| "grad_norm": 0.28028249740600586, | |
| "learning_rate": 7.148221227620408e-05, | |
| "loss": 0.2112, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1610949421851648, | |
| "grad_norm": 0.2596656382083893, | |
| "learning_rate": 6.395104899690134e-05, | |
| "loss": 0.268, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1661291591284512, | |
| "grad_norm": 0.2537478804588318, | |
| "learning_rate": 5.7075226940527376e-05, | |
| "loss": 0.296, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1711633760717376, | |
| "grad_norm": 0.2768983542919159, | |
| "learning_rate": 5.089933845158773e-05, | |
| "loss": 0.3204, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.176197593015024, | |
| "grad_norm": 0.2898544371128082, | |
| "learning_rate": 4.546343653681667e-05, | |
| "loss": 0.2659, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1812318099583104, | |
| "grad_norm": 0.3207743167877197, | |
| "learning_rate": 4.080277510605873e-05, | |
| "loss": 0.2555, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1862660269015968, | |
| "grad_norm": 0.34422051906585693, | |
| "learning_rate": 3.694758033713536e-05, | |
| "loss": 0.2692, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1913002438448832, | |
| "grad_norm": 0.22735346853733063, | |
| "learning_rate": 3.392285464748298e-05, | |
| "loss": 0.1795, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1963344607881696, | |
| "grad_norm": 0.20439870655536652, | |
| "learning_rate": 3.174821454388177e-05, | |
| "loss": 0.1755, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.201368677731456, | |
| "grad_norm": 0.1964559704065323, | |
| "learning_rate": 3.0437763401881657e-05, | |
| "loss": 0.1648, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20640289467474238, | |
| "grad_norm": 0.2255191057920456, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.1903, | |
| "step": 41 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 41, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 20, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.706513174269788e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |