| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028914269191846177, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005782853838369235, | |
| "grad_norm": 0.3306373357772827, | |
| "learning_rate": 5e-06, | |
| "loss": 0.843, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005782853838369235, | |
| "eval_loss": 0.9051669239997864, | |
| "eval_runtime": 26.4054, | |
| "eval_samples_per_second": 27.608, | |
| "eval_steps_per_second": 13.823, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001156570767673847, | |
| "grad_norm": 0.47444525361061096, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9431, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0017348561515107706, | |
| "grad_norm": 0.3817633390426636, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.8436, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002313141535347694, | |
| "grad_norm": 0.4596897065639496, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9052, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028914269191846176, | |
| "grad_norm": 0.4641701281070709, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.9076, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0034697123030215412, | |
| "grad_norm": 0.4002288579940796, | |
| "learning_rate": 3e-05, | |
| "loss": 0.7742, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004047997686858464, | |
| "grad_norm": 0.40169280767440796, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.8444, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004626283070695388, | |
| "grad_norm": 0.5613084435462952, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0238, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005204568454532312, | |
| "grad_norm": 0.6021634340286255, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.9818, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005782853838369235, | |
| "grad_norm": 0.4571888744831085, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8416, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006361139222206159, | |
| "grad_norm": 0.5815986394882202, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.9123, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0069394246060430825, | |
| "grad_norm": 0.6056288480758667, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.8216, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007517709989880006, | |
| "grad_norm": 0.6877990365028381, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.8851, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007517709989880006, | |
| "eval_loss": 0.8058395385742188, | |
| "eval_runtime": 24.6769, | |
| "eval_samples_per_second": 29.542, | |
| "eval_steps_per_second": 14.791, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008095995373716929, | |
| "grad_norm": 0.56659334897995, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.8059, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008674280757553852, | |
| "grad_norm": 0.484801709651947, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.7943, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009252566141390776, | |
| "grad_norm": 0.668626070022583, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.8542, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0098308515252277, | |
| "grad_norm": 0.5725303292274475, | |
| "learning_rate": 4.6316004108852305e-05, | |
| "loss": 0.7044, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010409136909064623, | |
| "grad_norm": 0.6510726809501648, | |
| "learning_rate": 4.522542485937369e-05, | |
| "loss": 0.7037, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010987422292901547, | |
| "grad_norm": 0.6378070116043091, | |
| "learning_rate": 4.401014914000078e-05, | |
| "loss": 0.7157, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01156570767673847, | |
| "grad_norm": 0.7792880535125732, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.7768, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012143993060575394, | |
| "grad_norm": 0.46598246693611145, | |
| "learning_rate": 4.123620120825459e-05, | |
| "loss": 0.5836, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012722278444412318, | |
| "grad_norm": 0.8034200668334961, | |
| "learning_rate": 3.969463130731183e-05, | |
| "loss": 0.7133, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.013300563828249241, | |
| "grad_norm": 0.7533989548683167, | |
| "learning_rate": 3.8062464117898724e-05, | |
| "loss": 0.6965, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.013878849212086165, | |
| "grad_norm": 0.5304470062255859, | |
| "learning_rate": 3.634976249348867e-05, | |
| "loss": 0.6367, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014457134595923089, | |
| "grad_norm": 0.7445480823516846, | |
| "learning_rate": 3.456708580912725e-05, | |
| "loss": 0.6986, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015035419979760012, | |
| "grad_norm": 0.8515669703483582, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.6763, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.015035419979760012, | |
| "eval_loss": 0.6640514135360718, | |
| "eval_runtime": 24.6725, | |
| "eval_samples_per_second": 29.547, | |
| "eval_steps_per_second": 14.794, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.015613705363596936, | |
| "grad_norm": 0.5554443597793579, | |
| "learning_rate": 3.083613409639764e-05, | |
| "loss": 0.6288, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.016191990747433858, | |
| "grad_norm": 0.6648669838905334, | |
| "learning_rate": 2.8910861626005776e-05, | |
| "loss": 0.6552, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.016770276131270783, | |
| "grad_norm": 0.728183925151825, | |
| "learning_rate": 2.6961477393196126e-05, | |
| "loss": 0.6793, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.017348561515107705, | |
| "grad_norm": 0.5944912433624268, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6537, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01792684689894463, | |
| "grad_norm": 0.6181674599647522, | |
| "learning_rate": 2.303852260680388e-05, | |
| "loss": 0.6846, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.018505132282781552, | |
| "grad_norm": 0.8404297232627869, | |
| "learning_rate": 2.1089138373994223e-05, | |
| "loss": 0.7196, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.019083417666618478, | |
| "grad_norm": 0.706020176410675, | |
| "learning_rate": 1.9163865903602374e-05, | |
| "loss": 0.6079, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0196617030504554, | |
| "grad_norm": 0.7011454701423645, | |
| "learning_rate": 1.7274575140626318e-05, | |
| "loss": 0.7039, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.020239988434292325, | |
| "grad_norm": 0.6933149695396423, | |
| "learning_rate": 1.5432914190872757e-05, | |
| "loss": 0.6284, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.020818273818129247, | |
| "grad_norm": 0.7218239903450012, | |
| "learning_rate": 1.3650237506511331e-05, | |
| "loss": 0.6569, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.021396559201966172, | |
| "grad_norm": 0.7234783172607422, | |
| "learning_rate": 1.1937535882101281e-05, | |
| "loss": 0.6429, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.021974844585803094, | |
| "grad_norm": 0.5774780511856079, | |
| "learning_rate": 1.0305368692688174e-05, | |
| "loss": 0.5611, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.022553129969640016, | |
| "grad_norm": 0.7207251191139221, | |
| "learning_rate": 8.763798791745411e-06, | |
| "loss": 0.6489, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.022553129969640016, | |
| "eval_loss": 0.6252636909484863, | |
| "eval_runtime": 24.6955, | |
| "eval_samples_per_second": 29.52, | |
| "eval_steps_per_second": 14.78, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02313141535347694, | |
| "grad_norm": 0.6595151424407959, | |
| "learning_rate": 7.3223304703363135e-06, | |
| "loss": 0.6198, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.023709700737313863, | |
| "grad_norm": 0.7210184931755066, | |
| "learning_rate": 5.989850859999227e-06, | |
| "loss": 0.607, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02428798612115079, | |
| "grad_norm": 0.7432602643966675, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.6241, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02486627150498771, | |
| "grad_norm": 0.7371325492858887, | |
| "learning_rate": 3.6839958911476957e-06, | |
| "loss": 0.639, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.025444556888824636, | |
| "grad_norm": 0.690451979637146, | |
| "learning_rate": 2.7248368952908053e-06, | |
| "loss": 0.6563, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.026022842272661557, | |
| "grad_norm": 0.6509324312210083, | |
| "learning_rate": 1.9030116872178316e-06, | |
| "loss": 0.5702, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.026601127656498483, | |
| "grad_norm": 0.6391157507896423, | |
| "learning_rate": 1.2235870926211619e-06, | |
| "loss": 0.6043, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.027179413040335405, | |
| "grad_norm": 0.7080129384994507, | |
| "learning_rate": 6.907519900580861e-07, | |
| "loss": 0.6471, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02775769842417233, | |
| "grad_norm": 0.6260955333709717, | |
| "learning_rate": 3.077914851215585e-07, | |
| "loss": 0.6057, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.028335983808009252, | |
| "grad_norm": 0.7455611824989319, | |
| "learning_rate": 7.706665667180091e-08, | |
| "loss": 0.649, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.028914269191846177, | |
| "grad_norm": 0.7520791292190552, | |
| "learning_rate": 0.0, | |
| "loss": 0.6281, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9617734090358784.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |