| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9979188345473466, | |
| "eval_steps": 500, | |
| "global_step": 480, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04162330905306972, | |
| "grad_norm": 0.7745468616485596, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7706, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08324661810613944, | |
| "grad_norm": 0.5561801791191101, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6448, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12486992715920915, | |
| "grad_norm": 0.23404787480831146, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4716, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16649323621227888, | |
| "grad_norm": 0.18818368017673492, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3672, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2081165452653486, | |
| "grad_norm": 0.18688304722309113, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2657, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2497398543184183, | |
| "grad_norm": 0.1951465606689453, | |
| "learning_rate": 0.00012, | |
| "loss": 1.125, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.29136316337148804, | |
| "grad_norm": 0.1746235191822052, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1003, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.33298647242455776, | |
| "grad_norm": 0.20920881628990173, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0207, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.37460978147762747, | |
| "grad_norm": 0.22199565172195435, | |
| "learning_rate": 0.00018, | |
| "loss": 0.9757, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4162330905306972, | |
| "grad_norm": 0.18666373193264008, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9414, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4578563995837669, | |
| "grad_norm": 0.2139161080121994, | |
| "learning_rate": 0.000199658449300667, | |
| "loss": 0.9025, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4994797086368366, | |
| "grad_norm": 0.19018647074699402, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.904, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5411030176899063, | |
| "grad_norm": 0.28649064898490906, | |
| "learning_rate": 0.00019694002659393305, | |
| "loss": 0.9177, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5827263267429761, | |
| "grad_norm": 0.21059155464172363, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.8929, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6243496357960457, | |
| "grad_norm": 0.21605370938777924, | |
| "learning_rate": 0.00019157733266550575, | |
| "loss": 0.8692, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6659729448491155, | |
| "grad_norm": 0.204218327999115, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.8661, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7075962539021852, | |
| "grad_norm": 0.20825326442718506, | |
| "learning_rate": 0.00018371664782625287, | |
| "loss": 0.8508, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7492195629552549, | |
| "grad_norm": 0.21748915314674377, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.8912, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7908428720083247, | |
| "grad_norm": 0.21721281111240387, | |
| "learning_rate": 0.00017357239106731317, | |
| "loss": 0.8368, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8324661810613944, | |
| "grad_norm": 0.2268160879611969, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.8407, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8740894901144641, | |
| "grad_norm": 0.25088444352149963, | |
| "learning_rate": 0.0001614212712689668, | |
| "loss": 0.8206, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9157127991675338, | |
| "grad_norm": 0.2083650529384613, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.8191, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9573361082206036, | |
| "grad_norm": 0.20936889946460724, | |
| "learning_rate": 0.00014759473930370736, | |
| "loss": 0.8103, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9989594172736732, | |
| "grad_norm": 0.2282739132642746, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.7974, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.0405827263267429, | |
| "grad_norm": 0.22600172460079193, | |
| "learning_rate": 0.00013246994692046836, | |
| "loss": 0.847, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.0822060353798126, | |
| "grad_norm": 0.22329868376255035, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.8268, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.1238293444328824, | |
| "grad_norm": 0.24019195139408112, | |
| "learning_rate": 0.00011645945902807341, | |
| "loss": 0.7869, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1654526534859522, | |
| "grad_norm": 0.24571700394153595, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.7997, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.207075962539022, | |
| "grad_norm": 0.24582228064537048, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8127, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.2486992715920915, | |
| "grad_norm": 0.23523323237895966, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 0.7951, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 0.2251071184873581, | |
| "learning_rate": 8.35405409719266e-05, | |
| "loss": 0.7968, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.331945889698231, | |
| "grad_norm": 0.27596697211265564, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 0.8039, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.3735691987513008, | |
| "grad_norm": 0.2557406723499298, | |
| "learning_rate": 6.753005307953167e-05, | |
| "loss": 0.8214, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.4151925078043703, | |
| "grad_norm": 0.24903537333011627, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 0.7744, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.45681581685744, | |
| "grad_norm": 0.24901647865772247, | |
| "learning_rate": 5.240526069629265e-05, | |
| "loss": 0.7886, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.4984391259105099, | |
| "grad_norm": 0.23960117995738983, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 0.7917, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.5400624349635796, | |
| "grad_norm": 0.2526036202907562, | |
| "learning_rate": 3.857872873103322e-05, | |
| "loss": 0.7811, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.5816857440166494, | |
| "grad_norm": 0.24781571328639984, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 0.769, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.6233090530697192, | |
| "grad_norm": 0.24783489108085632, | |
| "learning_rate": 2.6427608932686843e-05, | |
| "loss": 0.7746, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.6649323621227887, | |
| "grad_norm": 0.2527744472026825, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 0.7518, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.7065556711758585, | |
| "grad_norm": 0.24453039467334747, | |
| "learning_rate": 1.6283352173747145e-05, | |
| "loss": 0.7763, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.748178980228928, | |
| "grad_norm": 0.2481396645307541, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 0.7949, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.7898022892819978, | |
| "grad_norm": 0.2535879611968994, | |
| "learning_rate": 8.422667334494249e-06, | |
| "loss": 0.781, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.8314255983350676, | |
| "grad_norm": 0.24758380651474, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 0.7376, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.8730489073881373, | |
| "grad_norm": 0.25179538130760193, | |
| "learning_rate": 3.059973406066963e-06, | |
| "loss": 0.7679, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.914672216441207, | |
| "grad_norm": 0.2668040990829468, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 0.7577, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.9562955254942769, | |
| "grad_norm": 0.2509586215019226, | |
| "learning_rate": 3.415506993330153e-07, | |
| "loss": 0.7456, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.9979188345473466, | |
| "grad_norm": 0.25124892592430115, | |
| "learning_rate": 0.0, | |
| "loss": 0.7852, | |
| "step": 480 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 480, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.682197897510912e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |