| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.49261083743842365, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012315270935960592, | |
| "grad_norm": 0.15056075155735016, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 1.9444, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024630541871921183, | |
| "grad_norm": 0.13297975063323975, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.9366, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03694581280788178, | |
| "grad_norm": 0.1540609449148178, | |
| "learning_rate": 1.999872198665273e-05, | |
| "loss": 1.8808, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04926108374384237, | |
| "grad_norm": 0.1933898627758026, | |
| "learning_rate": 1.9984348087759785e-05, | |
| "loss": 1.9214, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06157635467980296, | |
| "grad_norm": 0.18024365603923798, | |
| "learning_rate": 1.9954025809828266e-05, | |
| "loss": 1.8184, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07389162561576355, | |
| "grad_norm": 0.16980205476284027, | |
| "learning_rate": 1.9907803587786273e-05, | |
| "loss": 1.8755, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08620689655172414, | |
| "grad_norm": 0.19214530289173126, | |
| "learning_rate": 1.9845755254147526e-05, | |
| "loss": 1.7953, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09852216748768473, | |
| "grad_norm": 0.16766290366649628, | |
| "learning_rate": 1.976797992107587e-05, | |
| "loss": 1.8465, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11083743842364532, | |
| "grad_norm": 0.16648121178150177, | |
| "learning_rate": 1.967460182206965e-05, | |
| "loss": 1.7997, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12315270935960591, | |
| "grad_norm": 0.1676236242055893, | |
| "learning_rate": 1.9565770113518827e-05, | |
| "loss": 1.7335, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1354679802955665, | |
| "grad_norm": 0.17232279479503632, | |
| "learning_rate": 1.9441658636451794e-05, | |
| "loss": 1.7366, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1477832512315271, | |
| "grad_norm": 0.1846841275691986, | |
| "learning_rate": 1.9302465638852484e-05, | |
| "loss": 1.6742, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16009852216748768, | |
| "grad_norm": 0.16829562187194824, | |
| "learning_rate": 1.9148413458991325e-05, | |
| "loss": 1.6856, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1724137931034483, | |
| "grad_norm": 0.20127680897712708, | |
| "learning_rate": 1.897974817027588e-05, | |
| "loss": 1.7264, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18472906403940886, | |
| "grad_norm": 0.18983212113380432, | |
| "learning_rate": 1.8796739188188396e-05, | |
| "loss": 1.7261, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19704433497536947, | |
| "grad_norm": 0.18018069863319397, | |
| "learning_rate": 1.8599678839938237e-05, | |
| "loss": 1.6785, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20935960591133004, | |
| "grad_norm": 0.1833820790052414, | |
| "learning_rate": 1.83888818975165e-05, | |
| "loss": 1.7149, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22167487684729065, | |
| "grad_norm": 0.1864066869020462, | |
| "learning_rate": 1.8164685074898737e-05, | |
| "loss": 1.7233, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23399014778325122, | |
| "grad_norm": 0.18022508919239044, | |
| "learning_rate": 1.792744649019891e-05, | |
| "loss": 1.6605, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24630541871921183, | |
| "grad_norm": 0.20446862280368805, | |
| "learning_rate": 1.7677545093633713e-05, | |
| "loss": 1.7045, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25862068965517243, | |
| "grad_norm": 0.19190183281898499, | |
| "learning_rate": 1.7415380062210956e-05, | |
| "loss": 1.7179, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.270935960591133, | |
| "grad_norm": 0.1983891725540161, | |
| "learning_rate": 1.7141370162108973e-05, | |
| "loss": 1.6844, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2832512315270936, | |
| "grad_norm": 0.20192717015743256, | |
| "learning_rate": 1.685595307976545e-05, | |
| "loss": 1.7233, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2955665024630542, | |
| "grad_norm": 0.20578549802303314, | |
| "learning_rate": 1.6559584722744228e-05, | |
| "loss": 1.6564, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3078817733990148, | |
| "grad_norm": 0.21980562806129456, | |
| "learning_rate": 1.6252738491496826e-05, | |
| "loss": 1.669, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.32019704433497537, | |
| "grad_norm": 0.2122306525707245, | |
| "learning_rate": 1.5935904523181872e-05, | |
| "loss": 1.643, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33251231527093594, | |
| "grad_norm": 0.2168055772781372, | |
| "learning_rate": 1.5609588908750378e-05, | |
| "loss": 1.6618, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.3448275862068966, | |
| "grad_norm": 0.2982899248600006, | |
| "learning_rate": 1.527431288454741e-05, | |
| "loss": 1.6878, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 0.23479227721691132, | |
| "learning_rate": 1.4930611999721457e-05, | |
| "loss": 1.666, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.3694581280788177, | |
| "grad_norm": 0.2242238074541092, | |
| "learning_rate": 1.4579035260771374e-05, | |
| "loss": 1.6629, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3817733990147783, | |
| "grad_norm": 0.23022723197937012, | |
| "learning_rate": 1.4220144254597445e-05, | |
| "loss": 1.6364, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.39408866995073893, | |
| "grad_norm": 0.25636643171310425, | |
| "learning_rate": 1.3854512251457248e-05, | |
| "loss": 1.636, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4064039408866995, | |
| "grad_norm": 0.24127626419067383, | |
| "learning_rate": 1.3482723289259258e-05, | |
| "loss": 1.6272, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.4187192118226601, | |
| "grad_norm": 0.24311544001102448, | |
| "learning_rate": 1.3105371240656894e-05, | |
| "loss": 1.5967, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.43103448275862066, | |
| "grad_norm": 0.23862501978874207, | |
| "learning_rate": 1.272305886443312e-05, | |
| "loss": 1.6619, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.4433497536945813, | |
| "grad_norm": 0.2440972477197647, | |
| "learning_rate": 1.233639684269092e-05, | |
| "loss": 1.6598, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.45566502463054187, | |
| "grad_norm": 0.2527645230293274, | |
| "learning_rate": 1.1946002805387538e-05, | |
| "loss": 1.6096, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.46798029556650245, | |
| "grad_norm": 0.27532511949539185, | |
| "learning_rate": 1.1552500343770658e-05, | |
| "loss": 1.6415, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4802955665024631, | |
| "grad_norm": 0.258892297744751, | |
| "learning_rate": 1.1156518014292366e-05, | |
| "loss": 1.6529, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.49261083743842365, | |
| "grad_norm": 0.2597699761390686, | |
| "learning_rate": 1.0758688334592034e-05, | |
| "loss": 1.6958, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 406, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.061755647321702e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |